diff --git a/model-00001-of-00045.safetensors b/model-00001-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68bc424cb42a060c71220b40411ece5f5f1bb2ea --- /dev/null +++ b/model-00001-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fa3d882ad1440217d26f2d0820e15d96cb7f72d6e74100b865aaa111aba2f03 +size 13147466360 diff --git a/model-00001-of-00052.safetensors b/model-00001-of-00052.safetensors deleted file mode 100644 index 4a8eb66ab4addfd99d2fa86b9d84ce92a5383cd1..0000000000000000000000000000000000000000 --- a/model-00001-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6ce83b986a9dd8da1947eff05543436bfe399d49701b54fed0428fa8a6ccb7dc -size 24637941608 diff --git a/model-00002-of-00045.safetensors b/model-00002-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3c5b787177b899a41c597d1fef8b2e1583be359b --- /dev/null +++ b/model-00002-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d706af50ee5a1e53e9e791d76685dc11e05477d36660f0f59342f46a0c33c80 +size 13147466360 diff --git a/model-00002-of-00052.safetensors b/model-00002-of-00052.safetensors deleted file mode 100644 index 97a8d2dc735ca033f9b842837dbed58acfb8d25c..0000000000000000000000000000000000000000 --- a/model-00002-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:75de3187877b7e352f1e8c914f73b08c59ca1db8ee9f16d5f567ab93ce87b7cf -size 32031266096 diff --git a/model-00003-of-00045.safetensors b/model-00003-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a7dbf9bdbbd470bfab9726a6914b2be2cdb16589 --- /dev/null +++ b/model-00003-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1779c9b9b540b862d280e866fe9477c2ed6f9112b75f0ff916e5ebfb385bf285 +size 13147466360 diff --git a/model-00003-of-00052.safetensors b/model-00003-of-00052.safetensors deleted file mode 100644 index 637b7e4be664b53e0662ac92aa4ae1febe855ffd..0000000000000000000000000000000000000000 --- a/model-00003-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:921f96f2396798d9bed610c00716a51b5db31465016202508bb08b6ded01bf63 -size 32221190328 diff --git a/model-00004-of-00045.safetensors b/model-00004-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..70386e24ddcd2460d123b836a5bf3b5fac6b7371 --- /dev/null +++ b/model-00004-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60125ad4f78ab34d9e821280cf72d57b1e97dde56541085ee1ff1499dfb38e1a +size 13147466360 diff --git a/model-00004-of-00052.safetensors b/model-00004-of-00052.safetensors deleted file mode 100644 index bca17e8c99119aecb9a6998a473bfba184e513f6..0000000000000000000000000000000000000000 --- a/model-00004-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f1a641c44d0758d87f20c7274af4db785d6bf8cfc3482451c29e99a723f57f08 -size 32031255232 diff --git a/model-00005-of-00045.safetensors b/model-00005-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a7dbc6e4c321bc8c865467c8b0688349a9b3ef5 --- /dev/null +++ b/model-00005-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd4c745f25b7a9e70513563328ebca422eba28f82bbf8b3a8d587e9ee687a694 +size 13147466360 diff --git a/model-00005-of-00052.safetensors b/model-00005-of-00052.safetensors deleted file mode 100644 index b40ca72d1920769547b367b53cea9cf15dfe56ef..0000000000000000000000000000000000000000 --- a/model-00005-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:aef00c50e41b9a20f46b1127a91aef5cc60feb46445e30e0bb94b792493c0c59 -size 32031266096 diff --git a/model-00006-of-00045.safetensors b/model-00006-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a0f146f59799a0dd670312a0b634ae22b0a6471 --- /dev/null +++ b/model-00006-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12be94bb10ef895f645dd805424aa35a3e1d348e2574a7f3829abc1c846cab9f +size 13147466760 diff --git a/model-00006-of-00052.safetensors b/model-00006-of-00052.safetensors deleted file mode 100644 index 5386b1e6c1f041bf7a000b7bbaabf4478064ebf1..0000000000000000000000000000000000000000 --- a/model-00006-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:98420334edc9db67bd9623c3963c705d561572a025550abb02a3b9a7e30f35ce -size 32221190328 diff --git a/model-00007-of-00045.safetensors b/model-00007-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..52774ffbd4cd7e691347d3e4d09e7c148990d504 --- /dev/null +++ b/model-00007-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee7dfc94bbd4fb6e73eb42ec624a4948af95f11f851d3a51225ef1f487f96c3 +size 13147466760 diff --git a/model-00007-of-00052.safetensors b/model-00007-of-00052.safetensors deleted file mode 100644 index 1c9dc381098d3756ddba1a2aa0e831f0e1233bcd..0000000000000000000000000000000000000000 --- a/model-00007-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:24863e2ef750228f1ed7d6bc121ede03f8355a71de4d613dc753d3f5f87b46e9 -size 12386383160 diff --git a/model-00008-of-00045.safetensors b/model-00008-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5dbd572fa60499f80f8ba4168abc31d857595f16 --- /dev/null +++ b/model-00008-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e028a75139090d8418b431fee2e79f221fd96a474cd3f8900e873d0c599bdba +size 13147466760 diff --git a/model-00008-of-00052.safetensors b/model-00008-of-00052.safetensors deleted file mode 100644 index 508052d76029d5b1f5f7ad7fe6d40bca09a21b33..0000000000000000000000000000000000000000 --- a/model-00008-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7be41b4c56e9582f4d135a03e1983d3f0c1a75d09c490d3e769a42dbe63ca09d -size 4987570560 diff --git a/model-00009-of-00045.safetensors b/model-00009-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82821ebf41abc0ab74f04f9ea79601e116006c32 --- /dev/null +++ b/model-00009-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db5f231cbb05705cf448ae6391abde9929758b386895884aac636e6e62fb00ac +size 13147466760 diff --git a/model-00009-of-00052.safetensors b/model-00009-of-00052.safetensors deleted file mode 100644 index 1082a1b1ca624bb1e840a783b3a4812907ca7712..0000000000000000000000000000000000000000 --- a/model-00009-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2c90ed2b86ac523865266168f5271813a955799167867e4743c2124f22ebc0ef -size 4987570560 diff --git a/model-00010-of-00045.safetensors b/model-00010-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8ec04336290e2147ca2ec8117c7ce9332f994451 --- /dev/null +++ b/model-00010-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5bfb1ba93b77c1da77975a59576d5987e81dc8fd4261f0a0cb324c8ddb2aac +size 13147466760 diff --git a/model-00010-of-00052.safetensors b/model-00010-of-00052.safetensors deleted file mode 100644 index a2a22a28da144a4b95ad7f02aa06a5ec8a42461d..0000000000000000000000000000000000000000 --- a/model-00010-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d9e7cd1e1dd8efd7df9a689952ec075e3236970b68b2174221ce33032561dc0a -size 4987570568 diff --git a/model-00011-of-00045.safetensors b/model-00011-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..268faa0f0f9ff4577943de29650c5208652664af --- /dev/null +++ b/model-00011-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37082a462bc7d0b0af25edf15662abc882b06fff2a8488677084537dae0a409c +size 13147466760 diff --git a/model-00011-of-00052.safetensors b/model-00011-of-00052.safetensors deleted file mode 100644 index 5c91675e2ed23ebb37bbad01366d64d4c9dc95a1..0000000000000000000000000000000000000000 --- a/model-00011-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a6ac4efedb6f327643ffe7f39550d0f6e56f512b58d7f50a7cb59da12da5c701 -size 4987570632 diff --git a/model-00012-of-00045.safetensors b/model-00012-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85cc84f8ddee541c37f06bc979b00e9d48f26e6b --- /dev/null +++ b/model-00012-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c8ca56d736e65b006f1da48a73f7adbec935c62cc19c5392c81a6fe53e3c19 +size 13147466760 diff --git a/model-00012-of-00052.safetensors b/model-00012-of-00052.safetensors deleted file mode 100644 index b22a85bed525cfcd2433a216ffbb718839373394..0000000000000000000000000000000000000000 --- a/model-00012-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:94dd4f7ca9ee2c2faf6c89d34d5bca7c79921821798800b01727e73e762545fd -size 4987570720 diff --git a/model-00013-of-00045.safetensors b/model-00013-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..51d6a241df43e74bfb72c910c7fd794da39726a4 --- /dev/null +++ b/model-00013-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1d942f9860063c79b5b28a886d44af947b19e434e410b65de113e260f4274da +size 13147466760 diff --git a/model-00013-of-00052.safetensors b/model-00013-of-00052.safetensors deleted file mode 100644 index 072c3073cbd428d80f11fd515ba22de3cb628284..0000000000000000000000000000000000000000 --- a/model-00013-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e9832cc5bc1853baa811d61ec4ffc08373a0cc1fec55480b49fdfe76f467dd0e -size 4987570720 diff --git a/model-00014-of-00045.safetensors b/model-00014-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63d0e6a89c690db81adecae84d64bd8ed0209c00 --- /dev/null +++ b/model-00014-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:121d41ff66ffa49b19888d79e995dcd821f93b2398d0c5e2fa3e744a72407592 +size 13147466760 diff --git a/model-00014-of-00052.safetensors b/model-00014-of-00052.safetensors deleted file mode 100644 index a4270c359eba85c38db3f384ea6378a486a1147a..0000000000000000000000000000000000000000 --- a/model-00014-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:31f083ca9288ccba4b62aab2897949385655f27b3ac9012aa1de9b23415796ef -size 4987570712 diff --git a/model-00015-of-00045.safetensors b/model-00015-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e4ab2b956c12c8ac131327015050a9b48c6d2fd6 --- /dev/null +++ b/model-00015-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2696eab3ea2deb6d264dc647f73bafc594387d3597c50bbef76caa2bad472653 +size 13147466760 diff --git a/model-00015-of-00052.safetensors b/model-00015-of-00052.safetensors deleted file mode 100644 index c9893640c0d51f83ec475e8721213c9afbdc36a9..0000000000000000000000000000000000000000 --- a/model-00015-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:30c6449634c123122aee1c75a5234def80b2a8a312811da9d4968bb3785c96db -size 4987570720 diff --git a/model-00016-of-00045.safetensors b/model-00016-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb6d163306c70a5b9745d0087a96b0d1eba3f80e --- /dev/null +++ b/model-00016-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f92421ed7c085472260deb67c4faa71f63918c02c94711f752153ca62b7097 +size 13147466760 diff --git a/model-00016-of-00052.safetensors b/model-00016-of-00052.safetensors deleted file mode 100644 index 77c5ebcacf56144a0e74b2ac39a1b6fe2b61dbca..0000000000000000000000000000000000000000 --- a/model-00016-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bf9454df79580a5296787cea715dc20947162bf92f14cefca38c13148a1197bd -size 4987570720 diff --git a/model-00017-of-00045.safetensors b/model-00017-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4309b5ad93e047ef03a81b89231315878bb74e54 --- /dev/null +++ b/model-00017-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2b4e7e3c9c385ede377e702a3142df1318f62b2bf3b44c14f3738e1945085e +size 13147466760 diff --git a/model-00017-of-00052.safetensors b/model-00017-of-00052.safetensors deleted file mode 100644 index e24093b5c6314a5b2cc42bad7f51de10a222bd3e..0000000000000000000000000000000000000000 --- a/model-00017-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8ae9e2c12d286b27d0c8496178222bad4bfc74c56bb6b7a79527735c3a0d4237 -size 4987570712 diff --git a/model-00018-of-00045.safetensors b/model-00018-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..54e7d6537de7e1018f25777dac7d6c55d6432206 --- /dev/null +++ b/model-00018-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee6cfec271c026b6229c0013c07b63ae371d9656708e7bd5b1fdb6e12a12b1e +size 13147466760 diff --git a/model-00018-of-00052.safetensors b/model-00018-of-00052.safetensors deleted file mode 100644 index 7e8bfc06c8b144716693d54bad34b4a31909f0c5..0000000000000000000000000000000000000000 --- a/model-00018-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:aa87ba759d9144ce7eea7c1f1fd381b88f710e8028762f1d8bb8d0d0b702cbc1 -size 4987570720 diff --git a/model-00019-of-00045.safetensors b/model-00019-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3aa4b2e9870a5f93d54bc102d5688af59a94acab --- /dev/null +++ b/model-00019-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8518650fb8e1befc2f91ff76ddd7eee795b4a98b3c62a8bac5bf39d303cb5bf3 +size 13147466760 diff --git a/model-00019-of-00052.safetensors b/model-00019-of-00052.safetensors deleted file mode 100644 index f1fd8c8a8160c98ef0316259ef6c613d11f4d2fc..0000000000000000000000000000000000000000 --- a/model-00019-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8a077da0d462a7c97e8b057c36ae64adea9932c2e80fa93e49cf63536208ae98 -size 4987570720 diff --git a/model-00020-of-00045.safetensors b/model-00020-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca33c6d75079342de5386619a16c61a9c7508b3e --- /dev/null +++ b/model-00020-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e3d0435bbbdec7a08c24d53d5a8baa2c368838adeeed38355e8ac4f866cc5fa +size 13147466760 diff --git a/model-00020-of-00052.safetensors b/model-00020-of-00052.safetensors deleted file mode 100644 index 5686b40c25ac9f28fd7492890828b99334d0448d..0000000000000000000000000000000000000000 --- a/model-00020-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7b5c93841e72b34567e6274e4a715a83727e2258abef299b8bad68426897c5b1 -size 4987570712 diff --git a/model-00021-of-00045.safetensors b/model-00021-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0fe0b6388b81be56480ed82aa4c768d4c90d85a3 --- /dev/null +++ b/model-00021-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd92bb37569e050a36e393ade3f111e63de25463c09e7bcab0e1e65fedd689d2 +size 13147466760 diff --git a/model-00021-of-00052.safetensors b/model-00021-of-00052.safetensors deleted file mode 100644 index c462df56070898967932248327b3a271e40c2b95..0000000000000000000000000000000000000000 --- a/model-00021-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dae2ae13a84b787ad7309840997c6f50cf0efbd4e3d172b339a20b5234bb5ccd -size 4987570720 diff --git a/model-00022-of-00045.safetensors b/model-00022-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..813518cb97b7ed98605476cdef7c937a346ac9ed --- /dev/null +++ b/model-00022-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4093ae3a4f199ade95cb60653e480760cb22e41df1d6c0c48f66501f6e01a80 +size 13147466760 diff --git a/model-00022-of-00052.safetensors b/model-00022-of-00052.safetensors deleted file mode 100644 index 3d76930137a97b5c229b8fd00c082566728a1208..0000000000000000000000000000000000000000 --- a/model-00022-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:419156551fba47c649a1e44fb13dc435ae382b48dd88e64fc8a84ebf9d5fd98c -size 4987570712 diff --git a/model-00023-of-00045.safetensors b/model-00023-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86641f3dad152162d6e12887e90d456464e33c03 --- /dev/null +++ b/model-00023-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1972bb12365e72196c891542852805a05e562460c9377d9d75099ff1f18a1637 +size 13147466760 diff --git a/model-00023-of-00052.safetensors b/model-00023-of-00052.safetensors deleted file mode 100644 index 53cc686ef8a38b1a47aa6e4f91ebe8442d6a75d8..0000000000000000000000000000000000000000 --- a/model-00023-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b5774604ab2ed957e167448f785b98b2d2c1f53fba99800d15de88008c57abe8 -size 4987570712 diff --git a/model-00024-of-00045.safetensors b/model-00024-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d29dd0c6d28637d3fd3999ba4eb57d557d2a8976 --- /dev/null +++ b/model-00024-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25c4e4c2964ddaacd91a8ac2f7a6d630c01ee6bf4d0b578b38ee93e45d2c53df +size 13147466760 diff --git a/model-00024-of-00052.safetensors b/model-00024-of-00052.safetensors deleted file mode 100644 index 6f229e4744ac0be29f4e8a6cff1a3c11f197ca33..0000000000000000000000000000000000000000 --- a/model-00024-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bec3429258566a3d57173fffce7ba3c624cfef389ffc9c4ecafd68676a162918 -size 4987570720 diff --git a/model-00025-of-00045.safetensors b/model-00025-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78768e5af6ae1a6bd082106b46078e53164b637c --- /dev/null +++ b/model-00025-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8126e78ce7d61811f78b0c17ea03cce0008be4a81ef2fb6a0454a86731e80862 +size 13147466760 diff --git a/model-00025-of-00052.safetensors b/model-00025-of-00052.safetensors deleted file mode 100644 index a5fe9a8c7866dc2ad61b4398a1342349faaef70b..0000000000000000000000000000000000000000 --- a/model-00025-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4f04d656063b498fca66732c33eaaa7b64f9858231a0bbb01dcc34aa548e628b -size 4987570712 diff --git a/model-00026-of-00045.safetensors b/model-00026-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f52dde9226346535ab7947bffa3f7a7730eab7bf --- /dev/null +++ b/model-00026-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e831063fb87610b83cb0de5678073b3173629a14e83d35c5a56ebe2f369d7cab +size 13147466760 diff --git a/model-00026-of-00052.safetensors b/model-00026-of-00052.safetensors deleted file mode 100644 index eb8470c9029dab1f871eed62e6df73928afe203c..0000000000000000000000000000000000000000 --- a/model-00026-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:273f69216f0b4b7ad8105fa7edaf4df4f498f9d62e35f441bf8c720d880d69bd -size 4987570720 diff --git a/model-00027-of-00045.safetensors b/model-00027-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ffb4994392103fa1f24d43d09d41c637be2ab8a0 --- /dev/null +++ b/model-00027-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9649022eb07165a75bd11dfedb68f42c2446ed74cba573792f90d7332355ed17 +size 13147466760 diff --git a/model-00027-of-00052.safetensors b/model-00027-of-00052.safetensors deleted file mode 100644 index a163f5b32bb485c45092ccd4253de8d1607bc8b6..0000000000000000000000000000000000000000 --- a/model-00027-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a24e9aac9f5f8b99a1af339eeed62e6259aee5937c8073fd71086d07a392c3e -size 4987570720 diff --git a/model-00028-of-00045.safetensors b/model-00028-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6444cd02a3832aa3e20b96398f3fea32d606ecfc --- /dev/null +++ b/model-00028-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e125662c2926312349f7d7ebc9f9c0d09ab36234488e6d9afc11f04e935a1de +size 13147466760 diff --git a/model-00028-of-00052.safetensors b/model-00028-of-00052.safetensors deleted file mode 100644 index 13fc1c4a49565558026ef02131105374b312daaa..0000000000000000000000000000000000000000 --- a/model-00028-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f15f7595e9c3755e50a2f1d086a228f4c23c94d714a36dab7c71054f98e10f4d -size 4987570712 diff --git a/model-00029-of-00045.safetensors b/model-00029-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bfe009c1a86519c5825a96f76aeb222b2ad9877a --- /dev/null +++ b/model-00029-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d31688ae64d65a9763a9df1279fb92d8265002e425d5e3b618c750ccfc1452 +size 13147466760 diff --git a/model-00029-of-00052.safetensors b/model-00029-of-00052.safetensors deleted file mode 100644 index f8ef372be23b5dd3ea5f2835db27ab7c74cd6f91..0000000000000000000000000000000000000000 --- a/model-00029-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8012c345358b5e3f16997a60ac227981aea528ea12de79d6e6d4bfcfa6056f62 -size 4987570720 diff --git a/model-00030-of-00045.safetensors b/model-00030-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca1f9599c6c39dd50020ffbb6661cd0be12949f0 --- /dev/null +++ b/model-00030-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8787c3b528bab422162b8c8489ed6432d6a969c1bddaae025fb20267a96ebbaf +size 13147466760 diff --git a/model-00030-of-00052.safetensors b/model-00030-of-00052.safetensors deleted file mode 100644 index f595a9a0ad6edd5cde6ef232bf45d724b579b114..0000000000000000000000000000000000000000 --- a/model-00030-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:af241f4d4acfaa9ffecae768dc7c618bfa6a81eb81149b953e93fcd0b46902b6 -size 4987570720 diff --git a/model-00031-of-00045.safetensors b/model-00031-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b28f6c9b6b26a9ff17490e971428793ebe33425 --- /dev/null +++ b/model-00031-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e34709c03416a3fdd6bb8431ea8041b6d939b5d69eaea30008ca0fe5f0a45536 +size 13147466760 diff --git a/model-00031-of-00052.safetensors b/model-00031-of-00052.safetensors deleted file mode 100644 index 0b78a05aa18310157e96e90c3f8dba52c8a4ad0f..0000000000000000000000000000000000000000 --- a/model-00031-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c869b5dfb7a5a4368a3a093c313d23d6d266fd3cf9efba2b8f405cbefc7ab109 -size 4987570712 diff --git a/model-00032-of-00045.safetensors b/model-00032-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..30ab906a0e5481696cf25bc4158d34b689e2e5cb --- /dev/null +++ b/model-00032-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7527e68967f536757cbf0e61931693c4edfb1dbe588e9e63ce22644859ebf1cb +size 13147466760 diff --git a/model-00032-of-00052.safetensors b/model-00032-of-00052.safetensors deleted file mode 100644 index 2adece1aab782e2e7879b50798ba3ddfa1ad34b4..0000000000000000000000000000000000000000 --- a/model-00032-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:605cfbe8a6233ea6b5ad304ca27298ac9c11974ca1257f61e997a3803e386a06 -size 4987570720 diff --git a/model-00033-of-00045.safetensors b/model-00033-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e62ada44244088a9328751ce6ed17e0d5329aec --- /dev/null +++ b/model-00033-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e28b9d3478aadee313f1e56f8a1825b9564ed34cacfd6bf6d08b160ef225db80 +size 13147466760 diff --git a/model-00033-of-00052.safetensors b/model-00033-of-00052.safetensors deleted file mode 100644 index 11242d8ae1444ee25f28c234e1bdd4f90fe03c90..0000000000000000000000000000000000000000 --- a/model-00033-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2fa6545eb879bd88dff7fa8eb64697f1ea09f74a14523d0b0519e9cf6d15f169 -size 4987570712 diff --git a/model-00034-of-00045.safetensors b/model-00034-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a88ee1c097c45dc12e841215ccaaec9040ae7fad --- /dev/null +++ b/model-00034-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7098dc149c5b2fe3425bdaecc35ad7a6c1d69ac5731b8fadf79f822ef5781e3 +size 13147466760 diff --git a/model-00034-of-00052.safetensors b/model-00034-of-00052.safetensors deleted file mode 100644 index a0336e04548f0c72c8107f9e4c75c369401b3355..0000000000000000000000000000000000000000 --- a/model-00034-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:69dfa29d6b65870b0cb36f5227ac4aaee2817d5b46754d9588298b3025ad1096 -size 4987570712 diff --git a/model-00035-of-00045.safetensors b/model-00035-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aeecb5f645d76b4525da6c57cb6eb0e1c69fbf28 --- /dev/null +++ b/model-00035-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba8787efe44ea5182eb9c346190f4396fa00e8b1de24cfaa534a16b2a662fda +size 13147466760 diff --git a/model-00035-of-00052.safetensors b/model-00035-of-00052.safetensors deleted file mode 100644 index 9b95073c090ba15e4d02fc9f57b053b8a9c386be..0000000000000000000000000000000000000000 --- a/model-00035-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3b17b15a136e875142a90e5859dc57817fef8ce0c8e0c50dcc17d3d9ac5594f9 -size 4987570720 diff --git a/model-00036-of-00045.safetensors b/model-00036-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab9121ee59550f416290c9a14105c8d1dc33ee25 --- /dev/null +++ b/model-00036-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a055d0918726beb397c4d30f3cf75d167ceaf83cb42976a7a864f4ae41b11775 +size 13147466760 diff --git a/model-00036-of-00052.safetensors b/model-00036-of-00052.safetensors deleted file mode 100644 index 6de6d190fec9d7d1c938882687f595a3fb050a69..0000000000000000000000000000000000000000 --- a/model-00036-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cdda596baf844882c9a39f4cef96564c1449f5c93c5f8552afa09831e44602c0 -size 4987570712 diff --git a/model-00037-of-00045.safetensors b/model-00037-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3f03371225547fa47a7af90d3e92fa8b90df994c --- /dev/null +++ b/model-00037-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf66b8cae7d5b4377495ef0f95bbc76b2dbb03be7f06401118406f53bc4f512f +size 13147466760 diff --git a/model-00037-of-00052.safetensors b/model-00037-of-00052.safetensors deleted file mode 100644 index b567d7fa6b30148d7d2926e52aa1c35ad418fd06..0000000000000000000000000000000000000000 --- a/model-00037-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1e4e1ba2bcc2fc34df74ce98856030179e93a81f4e4e0330037861df28474372 -size 4987570720 diff --git a/model-00038-of-00045.safetensors b/model-00038-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3259a4165f6104b3884550f254091531292931f7 --- /dev/null +++ b/model-00038-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d40621518b5f92a2aca61b13d75818c29e8e2d802bb96492912926af39dc64 +size 13147466760 diff --git a/model-00038-of-00052.safetensors b/model-00038-of-00052.safetensors deleted file mode 100644 index 9ced16606623253b89e0c4858339f4b001d68a50..0000000000000000000000000000000000000000 --- a/model-00038-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ed7e6936682bcc103d7565ee0078292700c7199d5d96c2474f582571b140617e -size 4987570720 diff --git a/model-00039-of-00045.safetensors b/model-00039-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..243b7a35c44f21ad3b8adc0e206e1215332e0027 --- /dev/null +++ b/model-00039-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6518c5fc946050ebd6993aed8d4855af90498216f6f0afd2737dfdde129e6b51 +size 13147466760 diff --git a/model-00039-of-00052.safetensors b/model-00039-of-00052.safetensors deleted file mode 100644 index 3c9d7a95153f8c45fbd1830b17c66ea6cbe8d01f..0000000000000000000000000000000000000000 --- a/model-00039-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bc084d2e0e7227d4243c23fdc03c846db171e01771ad8ca9b55cbe978136177a -size 4987570712 diff --git a/model-00040-of-00045.safetensors b/model-00040-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7cd472dd7c313e3a701f8cb5c1e09c630b071b47 --- /dev/null +++ b/model-00040-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591710ce27b81add35045dde5b0a421cd38db89b2ad23fac3d3bac9462261b30 +size 13147466760 diff --git a/model-00040-of-00052.safetensors b/model-00040-of-00052.safetensors deleted file mode 100644 index c6ad38658c0f0ebad48a3de5eae5c26bbe089b4f..0000000000000000000000000000000000000000 --- a/model-00040-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3cb5d29c90eab1826f0f39796081bb8aed6453086eb759f8e7149f1d0d505970 -size 4987570720 diff --git a/model-00041-of-00045.safetensors b/model-00041-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9328e036c19b19de5385fb8db8897548bff29080 --- /dev/null +++ b/model-00041-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:899700f680d217e2e901c5f4b8f0cee297059af71fbcc1152fed321e4b67604e +size 13147466760 diff --git a/model-00041-of-00052.safetensors b/model-00041-of-00052.safetensors deleted file mode 100644 index 4169d9d50ab7eaecf9b2d03f34940f403f96dd52..0000000000000000000000000000000000000000 --- a/model-00041-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cc36994a1b36c2152c4513f376fffa2a66d8c3ec6c9df0468d696ad75b9e3f07 -size 4987570720 diff --git a/model-00042-of-00045.safetensors b/model-00042-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..49dd33df85b438f504e3b9ddeecb1e86cc8acca3 --- /dev/null +++ b/model-00042-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8da30b46b8d6ae5c9ab801f45b2634ac75b2aece1d59bc8da2ae0529a7fe608 +size 13147466760 diff --git a/model-00042-of-00052.safetensors b/model-00042-of-00052.safetensors deleted file mode 100644 index 44d1e4c8f73ac534c8f6524180845b6b18816dfa..0000000000000000000000000000000000000000 --- a/model-00042-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3f329e67c647cc329966df75f298f007d14bd8de86a1d01aa4ffe9173b6c7be7 -size 4987570712 diff --git a/model-00043-of-00045.safetensors b/model-00043-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bdc472aed6a4e11574da11fe4c783a2fb574c315 --- /dev/null +++ b/model-00043-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eba850a6d473a7af3f0aa6412391ad37cefe661da82794232b21bfaffd99183 +size 13147466760 diff --git a/model-00043-of-00052.safetensors b/model-00043-of-00052.safetensors deleted file mode 100644 index fee6767077bb2336c4631ecfdfd57771b2c34429..0000000000000000000000000000000000000000 --- a/model-00043-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9b0462bf35c541ee70ac1301c937de8a9d11cdd0867a83e902e054eb327fb9aa -size 4987570720 diff --git a/model-00044-of-00045.safetensors b/model-00044-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aec7c4757b9a9c27451c5199adf4e66e9022cf08 --- /dev/null +++ b/model-00044-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a14653c7703b91bd0152a7d769fdd267bb2cba9838fc414bddee9b8a4f7db71 +size 13147466760 diff --git a/model-00044-of-00052.safetensors b/model-00044-of-00052.safetensors deleted file mode 100644 index 0e9ca2a491271e56da71f25d9e1f1cea0a2a1f60..0000000000000000000000000000000000000000 --- a/model-00044-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:99c301832548235ea405809d4cce43832953bbbaaf007131143f925c76ce4ab5 -size 4979309352 diff --git a/model-00045-of-00045.safetensors b/model-00045-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21381b2252af92340255a02c0d5ad05a9b0fd3be --- /dev/null +++ b/model-00045-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb0de3eaa0cfde1c4933d694c0f214d5c9d5b4ee1beaa086038b500f18d31af5 +size 2719492936 diff --git a/model-00045-of-00052.safetensors b/model-00045-of-00052.safetensors deleted file mode 100644 index b8e092a0f073480cd4611cecf5f39b0219ba8201..0000000000000000000000000000000000000000 --- a/model-00045-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f06c699c241c5df8a86be6b74904a400e1d0dfab5cec10f94464c4b5af746dd5 -size 4996794984 diff --git a/model-00046-of-00052.safetensors b/model-00046-of-00052.safetensors deleted file mode 100644 index c4db55bb952b9502332d054b66196a35d682c6a5..0000000000000000000000000000000000000000 --- a/model-00046-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dbcacb13095c4b981b561effafcafe78152cd15fc5761ae5fe7e51496aeaae39 -size 23946944776 diff --git a/model-00047-of-00052.safetensors b/model-00047-of-00052.safetensors deleted file mode 100644 index 28a3d129b6432ecbd1123e88f450eb4692159bd8..0000000000000000000000000000000000000000 --- a/model-00047-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:733adc6217ee3da1aa3c55815547e8062094d90f7386712797c62ee1009925e1 -size 39900565336 diff --git a/model-00048-of-00052.safetensors b/model-00048-of-00052.safetensors deleted file mode 100644 index 51be6fa2b4bbfa1ccc5d94b1d991f47ce1a65d2a..0000000000000000000000000000000000000000 --- a/model-00048-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e925e105f046655587ac5ba6a774c6a26a228bf9d765fa563c84fcc32e4b0076 -size 39900565344 diff --git a/model-00049-of-00052.safetensors b/model-00049-of-00052.safetensors deleted file mode 100644 index 9a08098d13ba502380a3ee45c01ac4cd986b48ec..0000000000000000000000000000000000000000 --- a/model-00049-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a198629080e467c7a4399d27a3af6c9e6ddfbb240c1e3a07f383c06b12e27044 -size 39900565336 diff --git a/model-00050-of-00052.safetensors b/model-00050-of-00052.safetensors deleted file mode 100644 index be067c98e293483837eddcf28c51527e8b612558..0000000000000000000000000000000000000000 --- a/model-00050-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:baef5bfbc5d26bf88a94feecd737436d15181051f853b1dfabdfe746a079a587 -size 39900565336 diff --git a/model-00051-of-00052.safetensors b/model-00051-of-00052.safetensors deleted file mode 100644 index adcdb7ad74c134874042bb58e53bace458acd904..0000000000000000000000000000000000000000 --- a/model-00051-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fc62b3cbe611e43c615a88d2c8644619f367ae27f84c4bd27bdf75921f6b3434 -size 9149384784 diff --git a/model-00052-of-00052.safetensors b/model-00052-of-00052.safetensors deleted file mode 100644 index 7da0f8ea032957e507bfbcd680fab2fbc97ca4c8..0000000000000000000000000000000000000000 --- a/model-00052-of-00052.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5aa40ddeb5f04493c85c9e5289246920f484b812dda598bcd5cf4c996fe07da3 -size 1420301752 diff --git a/model.safetensors.index.json b/model.safetensors.index.json index 95393973409e4cc483b32c3ef1015cd56cc4fdd7..90d6e97c4f7e856e6603783faeb1c34c3654a075 100644 --- a/model.safetensors.index.json +++ b/model.safetensors.index.json @@ -1,17610 +1,17610 @@ { "metadata": { - "total_size": 511321445376 + "total_size": 583925314560 }, "weight_map": { - "model.word_embeddings.weight": "model-00001-of-00052.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.0.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.40.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.41.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.42.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.43.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.44.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.45.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.46.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.47.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.48.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.49.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.50.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.51.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.52.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.53.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.54.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.55.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.56.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.57.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.58.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.59.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.60.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.61.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.62.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.0.mlp.experts.63.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.1.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.2.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.3.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.4.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.5.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.6.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.7.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.8.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.9.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.input_layernorm.weight": "model-00001-of-00052.safetensors", - "model.layers.10.attention.query_key_value.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00001-of-00052.safetensors", - "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.11.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.12.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.13.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.14.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.15.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.16.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.17.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.18.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.19.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.20.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.21.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.22.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.23.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.24.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.input_layernorm.weight": "model-00002-of-00052.safetensors", - "model.layers.25.attention.query_key_value.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00002-of-00052.safetensors", - "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.26.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.27.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.28.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.29.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.30.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.31.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.32.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.33.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.34.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.35.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.36.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.37.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.38.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.39.attention.query_key_value.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00003-of-00052.safetensors", - "model.layers.40.input_layernorm.weight": "model-00003-of-00052.safetensors", - "model.layers.40.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.41.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.42.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.43.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.44.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.45.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.46.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.47.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.47.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.48.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.48.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.49.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.49.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.50.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.50.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.51.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.51.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.52.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.52.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.53.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.40.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.41.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.42.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.43.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.44.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.45.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.46.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.47.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.48.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.49.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.50.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.51.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.52.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.53.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.54.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.55.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.56.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.57.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.58.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.59.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.60.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.61.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.62.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.53.mlp.experts.63.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.input_layernorm.weight": "model-00004-of-00052.safetensors", - "model.layers.54.attention.query_key_value.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.0.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.1.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.2.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.3.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.4.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.5.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.6.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.7.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.8.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.9.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.10.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.11.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.12.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.13.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.14.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.15.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.16.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.17.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.18.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.19.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.20.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.21.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.22.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.23.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.24.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.25.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.26.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.27.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.28.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.29.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.30.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.31.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.32.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.33.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.34.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.35.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.36.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.37.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.38.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.39.gate_proj.weight": "model-00004-of-00052.safetensors", - "model.layers.54.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.54.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.55.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.55.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.56.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.56.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.57.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.57.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.58.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.58.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.59.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.59.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.60.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.60.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.61.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.61.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.62.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.62.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.63.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.63.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.64.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.64.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.65.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.65.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.66.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.66.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.67.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.67.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.68.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.16.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.17.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.18.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.19.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.20.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.21.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.22.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.23.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.24.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.25.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.26.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.27.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.28.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.29.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.30.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.31.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.32.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.33.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.34.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.35.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.36.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.37.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.38.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.39.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.40.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.41.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.42.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.43.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.44.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.45.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.46.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.47.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.48.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.49.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.50.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.51.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.52.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.53.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.54.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.55.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.56.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.57.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.58.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.59.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.60.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.61.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.62.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.68.mlp.experts.63.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.input_layernorm.weight": "model-00005-of-00052.safetensors", - "model.layers.69.attention.query_key_value.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.0.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.1.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.2.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.3.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.4.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.5.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.6.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.7.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.8.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.9.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.10.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.11.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.12.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.13.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.14.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.15.gate_proj.weight": "model-00005-of-00052.safetensors", - "model.layers.69.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.69.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.70.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.70.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.71.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.71.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.72.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.72.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.73.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.73.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.74.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.74.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.75.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.75.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.76.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.76.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.77.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.77.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.78.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.78.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.79.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.79.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.80.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.80.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.81.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.81.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.82.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.82.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.83.attention.query_key_value.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.0.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.1.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.2.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.3.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.4.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.5.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.6.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.7.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.8.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.9.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.10.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.11.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.12.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.13.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.14.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.15.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.16.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.17.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.18.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.19.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.20.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.21.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.22.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.23.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.24.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.25.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.26.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.27.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.28.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.29.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.30.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.31.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.32.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.33.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.34.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.35.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.36.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.37.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.38.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.39.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.40.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.41.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.42.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.43.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.44.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.45.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.46.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.47.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.48.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.49.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.50.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.51.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.52.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.53.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.54.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.55.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.56.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.57.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.58.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.59.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.60.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.61.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.62.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.83.mlp.experts.63.gate_proj.weight": "model-00006-of-00052.safetensors", - "model.layers.84.input_layernorm.weight": "model-00006-of-00052.safetensors", - "model.layers.84.attention.query_key_value.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.0.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.1.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.2.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.3.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.4.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.5.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.6.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.7.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.8.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.9.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.10.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.11.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.12.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.13.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.14.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.15.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.16.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.17.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.18.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.19.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.20.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.21.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.22.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.23.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.24.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.25.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.26.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.27.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.28.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.29.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.30.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.31.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.32.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.33.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.34.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.35.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.36.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.37.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.38.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.39.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.40.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.41.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.42.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.43.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.44.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.45.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.46.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.47.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.48.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.49.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.50.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.51.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.52.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.53.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.54.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.55.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.56.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.57.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.58.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.59.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.60.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.61.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.62.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.84.mlp.experts.63.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.input_layernorm.weight": "model-00007-of-00052.safetensors", - "model.layers.85.attention.query_key_value.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.0.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.1.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.2.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.3.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.4.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.5.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.6.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.7.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.8.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.9.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.10.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.11.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.12.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.13.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.14.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.15.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.16.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.17.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.18.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.19.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.20.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.21.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.22.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.23.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.24.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.25.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.26.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.27.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.28.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.29.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.30.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.31.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.32.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.33.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.34.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.35.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.36.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.37.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.38.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.39.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.40.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.41.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.42.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.43.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.44.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.45.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.46.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.47.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.48.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.49.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.50.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.51.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.52.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.53.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.54.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.55.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.56.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.57.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.58.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.59.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.60.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.61.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.62.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.85.mlp.experts.63.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.input_layernorm.weight": "model-00007-of-00052.safetensors", - "model.layers.86.attention.query_key_value.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.0.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.1.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.2.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.3.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.4.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.5.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.6.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.7.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.8.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.9.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.10.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.11.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.12.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.13.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.14.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.15.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.16.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.17.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.18.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.19.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.20.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.21.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.22.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.23.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.24.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.25.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.26.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.27.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.28.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.29.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.30.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.31.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.32.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.33.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.34.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.35.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.36.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.37.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.38.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.39.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.40.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.41.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.42.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.43.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.44.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.45.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.46.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.47.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.48.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.49.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.50.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.51.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.52.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.53.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.54.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.55.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.56.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.57.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.58.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.59.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.60.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.61.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.62.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.86.mlp.experts.63.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.input_layernorm.weight": "model-00007-of-00052.safetensors", - "model.layers.87.attention.query_key_value.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.0.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.1.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.2.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.3.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.4.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.5.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.6.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.7.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.8.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.9.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.10.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.11.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.12.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.13.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.14.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.15.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.16.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.17.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.18.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.19.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.20.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.21.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.22.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.23.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.24.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.25.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.26.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.27.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.28.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.29.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.30.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.31.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.32.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.33.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.34.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.35.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.36.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.37.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.38.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.39.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.40.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.41.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.42.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.43.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.44.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.45.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.46.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.47.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.48.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.49.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.50.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.51.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.52.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.53.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.54.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.55.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.56.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.57.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.58.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.59.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.60.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.61.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.62.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.87.mlp.experts.63.gate_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.0.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.1.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.2.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.3.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.4.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.5.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.6.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.7.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.8.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.9.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.10.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.11.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.12.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.13.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.14.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.15.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.16.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.17.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.18.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.19.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.20.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.21.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.22.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.23.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.24.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.25.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.26.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.27.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.28.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.29.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.30.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.31.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.32.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.33.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.34.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.35.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.36.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.37.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.38.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.39.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.40.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.41.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.42.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.43.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.44.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.45.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.46.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.47.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.48.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.49.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.50.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.51.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.52.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.53.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.54.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.55.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.56.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.57.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.58.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.59.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.60.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.61.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.62.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.0.mlp.experts.63.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.0.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.1.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.2.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.3.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.4.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.5.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.6.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.7.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.8.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.9.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.10.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.11.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.12.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.13.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.14.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.15.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.16.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.17.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.18.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.19.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.20.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.21.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.22.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.23.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.24.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.25.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.26.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.27.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.28.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.29.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.30.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.31.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.32.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.33.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.34.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.35.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.36.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.37.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.38.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.39.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.40.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.41.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.42.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.43.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.44.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.45.down_proj.weight": "model-00007-of-00052.safetensors", - "model.layers.1.mlp.experts.46.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.47.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.48.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.49.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.50.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.51.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.52.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.53.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.54.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.55.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.56.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.57.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.58.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.59.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.60.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.61.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.62.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.1.mlp.experts.63.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.0.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.1.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.2.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.3.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.4.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.5.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.6.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.7.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.8.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.9.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.10.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.11.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.12.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.13.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.14.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.15.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.16.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.17.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.18.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.19.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.20.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.21.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.22.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.23.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.24.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.25.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.26.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.27.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.28.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.29.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.30.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.31.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.32.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.33.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.34.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.35.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.36.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.37.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.38.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.39.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.40.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.41.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.42.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.43.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.44.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.45.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.46.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.47.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.48.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.49.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.50.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.51.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.52.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.53.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.54.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.55.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.56.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.57.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.58.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.59.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.60.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.61.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.62.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.2.mlp.experts.63.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.0.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.1.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.2.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.3.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.4.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.5.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.6.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.7.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.8.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.9.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.10.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.11.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.12.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.13.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.14.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.15.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.16.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.17.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.18.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.19.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.20.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.21.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.22.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.23.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.24.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.25.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.26.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.27.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.28.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.29.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.30.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.31.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.32.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.33.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.34.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.35.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.36.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.37.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.38.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.39.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.40.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.41.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.42.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.43.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.44.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.45.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.46.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.47.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.48.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.49.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.50.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.51.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.52.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.53.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.54.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.55.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.56.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.57.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.58.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.59.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.60.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.61.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.62.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.3.mlp.experts.63.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.4.mlp.experts.0.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.4.mlp.experts.1.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.4.mlp.experts.2.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.4.mlp.experts.3.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.4.mlp.experts.4.down_proj.weight": "model-00008-of-00052.safetensors", - "model.layers.4.mlp.experts.5.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.6.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.7.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.8.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.9.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.10.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.11.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.12.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.13.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.14.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.15.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.16.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.17.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.18.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.19.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.20.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.21.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.22.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.23.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.24.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.25.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.26.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.27.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.28.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.29.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.30.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.31.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.32.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.33.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.34.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.35.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.36.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.37.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.38.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.39.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.40.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.41.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.42.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.43.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.44.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.45.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.46.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.47.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.48.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.49.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.50.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.51.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.52.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.53.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.54.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.55.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.56.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.57.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.58.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.59.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.60.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.61.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.62.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.4.mlp.experts.63.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.0.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.1.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.2.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.3.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.4.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.5.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.6.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.7.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.8.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.9.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.10.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.11.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.12.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.13.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.14.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.15.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.16.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.17.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.18.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.19.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.20.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.21.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.22.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.23.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.24.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.25.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.26.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.27.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.28.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.29.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.30.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.31.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.32.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.33.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.34.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.35.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.36.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.37.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.38.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.39.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.40.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.41.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.42.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.43.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.44.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.45.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.46.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.47.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.48.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.49.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.50.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.51.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.52.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.53.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.54.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.55.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.56.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.57.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.58.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.59.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.60.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.61.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.62.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.5.mlp.experts.63.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.0.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.1.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.2.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.3.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.4.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.5.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.6.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.7.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.8.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.9.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.10.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.11.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.12.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.13.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.14.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.15.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.16.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.17.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.18.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.19.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.20.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.21.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.22.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.23.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.24.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.25.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.26.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.27.down_proj.weight": "model-00009-of-00052.safetensors", - "model.layers.6.mlp.experts.28.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.29.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.30.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.31.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.32.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.33.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.34.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.35.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.36.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.37.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.38.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.39.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.40.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.41.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.42.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.43.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.44.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.45.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.46.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.47.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.48.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.49.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.50.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.51.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.52.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.53.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.54.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.55.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.56.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.57.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.58.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.59.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.60.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.61.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.62.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.6.mlp.experts.63.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.0.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.1.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.2.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.3.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.4.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.5.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.6.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.7.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.8.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.9.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.10.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.11.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.12.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.13.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.14.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.15.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.16.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.17.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.18.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.19.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.20.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.21.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.22.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.23.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.24.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.25.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.26.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.27.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.28.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.29.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.30.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.31.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.32.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.33.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.34.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.35.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.36.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.37.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.38.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.39.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.40.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.41.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.42.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.43.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.44.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.45.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.46.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.47.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.48.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.49.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.50.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.51.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.52.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.53.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.54.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.55.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.56.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.57.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.58.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.59.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.60.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.61.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.62.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.7.mlp.experts.63.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.0.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.1.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.2.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.3.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.4.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.5.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.6.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.7.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.8.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.9.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.10.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.11.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.12.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.13.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.14.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.15.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.16.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.17.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.18.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.19.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.20.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.21.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.22.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.23.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.24.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.25.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.26.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.27.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.28.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.29.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.30.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.31.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.32.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.33.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.34.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.35.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.36.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.37.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.38.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.39.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.40.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.41.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.42.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.43.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.44.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.45.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.46.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.47.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.48.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.49.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.50.down_proj.weight": "model-00010-of-00052.safetensors", - "model.layers.8.mlp.experts.51.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.52.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.53.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.54.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.55.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.56.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.57.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.58.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.59.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.60.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.61.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.62.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.8.mlp.experts.63.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.0.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.1.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.2.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.3.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.4.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.5.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.6.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.7.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.8.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.9.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.10.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.11.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.12.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.13.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.14.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.15.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.16.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.17.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.18.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.19.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.20.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.21.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.22.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.23.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.24.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.25.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.26.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.27.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.28.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.29.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.30.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.31.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.32.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.33.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.34.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.35.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.36.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.37.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.38.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.39.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.40.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.41.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.42.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.43.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.44.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.45.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.46.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.47.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.48.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.49.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.50.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.51.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.52.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.53.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.54.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.55.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.56.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.57.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.58.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.59.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.60.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.61.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.62.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.9.mlp.experts.63.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.0.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.1.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.2.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.3.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.4.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.5.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.6.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.7.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.8.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.9.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.10.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.11.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.12.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.13.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.14.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.15.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.16.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.17.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.18.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.19.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.20.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.21.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.22.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.23.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.24.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.25.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.26.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.27.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.28.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.29.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.30.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.31.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.32.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.33.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.34.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.35.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.36.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.37.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.38.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.39.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.40.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.41.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.42.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.43.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.44.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.45.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.46.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.47.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.48.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.49.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.50.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.51.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.52.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.53.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.54.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.55.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.56.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.57.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.58.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.59.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.60.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.61.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.62.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.10.mlp.experts.63.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.0.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.1.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.2.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.3.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.4.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.5.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.6.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.7.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.8.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.9.down_proj.weight": "model-00011-of-00052.safetensors", - "model.layers.11.mlp.experts.10.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.11.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.12.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.13.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.14.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.15.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.16.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.17.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.18.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.19.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.20.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.21.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.22.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.23.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.24.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.25.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.26.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.27.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.28.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.29.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.30.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.31.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.32.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.33.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.34.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.35.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.36.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.37.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.38.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.39.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.40.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.41.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.42.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.43.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.44.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.45.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.46.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.47.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.48.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.49.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.50.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.51.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.52.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.53.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.54.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.55.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.56.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.57.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.58.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.59.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.60.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.61.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.62.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.11.mlp.experts.63.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.0.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.1.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.2.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.3.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.4.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.5.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.6.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.7.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.8.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.9.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.10.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.11.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.12.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.13.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.14.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.15.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.16.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.17.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.18.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.19.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.20.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.21.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.22.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.23.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.24.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.25.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.26.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.27.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.28.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.29.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.30.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.31.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.32.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.33.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.34.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.35.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.36.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.37.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.38.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.39.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.40.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.41.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.42.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.43.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.44.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.45.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.46.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.47.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.48.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.49.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.50.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.51.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.52.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.53.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.54.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.55.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.56.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.57.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.58.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.59.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.60.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.61.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.62.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.12.mlp.experts.63.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.0.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.1.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.2.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.3.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.4.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.5.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.6.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.7.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.8.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.9.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.10.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.11.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.12.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.13.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.14.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.15.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.16.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.17.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.18.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.19.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.20.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.21.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.22.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.23.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.24.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.25.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.26.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.27.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.28.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.29.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.30.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.31.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.32.down_proj.weight": "model-00012-of-00052.safetensors", - "model.layers.13.mlp.experts.33.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.34.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.35.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.36.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.37.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.38.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.39.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.40.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.41.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.42.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.43.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.44.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.45.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.46.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.47.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.48.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.49.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.50.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.51.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.52.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.53.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.54.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.55.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.56.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.57.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.58.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.59.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.60.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.61.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.62.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.13.mlp.experts.63.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.0.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.1.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.2.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.3.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.4.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.5.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.6.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.7.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.8.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.9.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.10.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.11.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.12.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.13.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.14.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.15.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.16.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.17.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.18.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.19.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.20.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.21.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.22.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.23.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.24.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.25.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.26.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.27.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.28.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.29.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.30.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.31.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.32.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.33.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.34.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.35.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.36.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.37.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.38.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.39.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.40.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.41.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.42.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.43.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.44.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.45.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.46.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.47.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.48.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.49.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.50.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.51.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.52.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.53.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.54.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.55.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.56.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.57.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.58.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.59.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.60.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.61.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.62.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.14.mlp.experts.63.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.0.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.1.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.2.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.3.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.4.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.5.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.6.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.7.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.8.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.9.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.10.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.11.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.12.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.13.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.14.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.15.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.16.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.17.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.18.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.19.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.20.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.21.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.22.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.23.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.24.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.25.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.26.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.27.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.28.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.29.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.30.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.31.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.32.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.33.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.34.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.35.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.36.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.37.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.38.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.39.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.40.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.41.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.42.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.43.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.44.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.45.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.46.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.47.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.48.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.49.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.50.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.51.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.52.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.53.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.54.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.55.down_proj.weight": "model-00013-of-00052.safetensors", - "model.layers.15.mlp.experts.56.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.15.mlp.experts.57.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.15.mlp.experts.58.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.15.mlp.experts.59.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.15.mlp.experts.60.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.15.mlp.experts.61.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.15.mlp.experts.62.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.15.mlp.experts.63.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.0.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.1.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.2.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.3.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.4.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.5.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.6.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.7.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.8.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.9.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.10.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.11.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.12.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.13.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.14.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.15.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.16.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.17.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.18.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.19.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.20.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.21.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.22.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.23.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.24.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.25.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.26.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.27.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.28.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.29.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.30.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.31.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.32.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.33.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.34.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.35.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.36.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.37.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.38.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.39.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.40.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.41.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.42.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.43.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.44.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.45.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.46.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.47.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.48.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.49.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.50.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.51.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.52.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.53.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.54.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.55.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.56.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.57.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.58.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.59.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.60.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.61.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.62.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.16.mlp.experts.63.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.0.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.1.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.2.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.3.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.4.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.5.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.6.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.7.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.8.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.9.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.10.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.11.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.12.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.13.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.14.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.15.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.16.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.17.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.18.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.19.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.20.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.21.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.22.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.23.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.24.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.25.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.26.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.27.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.28.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.29.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.30.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.31.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.32.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.33.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.34.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.35.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.36.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.37.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.38.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.39.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.40.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.41.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.42.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.43.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.44.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.45.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.46.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.47.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.48.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.49.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.50.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.51.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.52.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.53.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.54.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.55.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.56.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.57.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.58.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.59.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.60.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.61.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.62.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.17.mlp.experts.63.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.0.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.1.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.2.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.3.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.4.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.5.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.6.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.7.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.8.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.9.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.10.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.11.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.12.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.13.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.14.down_proj.weight": "model-00014-of-00052.safetensors", - "model.layers.18.mlp.experts.15.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.16.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.17.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.18.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.19.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.20.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.21.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.22.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.23.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.24.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.25.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.26.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.27.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.28.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.29.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.30.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.31.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.32.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.33.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.34.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.35.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.36.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.37.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.38.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.39.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.40.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.41.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.42.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.43.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.44.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.45.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.46.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.47.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.48.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.49.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.50.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.51.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.52.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.53.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.54.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.55.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.56.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.57.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.58.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.59.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.60.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.61.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.62.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.18.mlp.experts.63.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.0.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.1.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.2.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.3.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.4.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.5.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.6.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.7.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.8.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.9.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.10.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.11.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.12.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.13.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.14.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.15.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.16.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.17.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.18.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.19.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.20.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.21.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.22.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.23.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.24.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.25.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.26.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.27.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.28.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.29.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.30.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.31.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.32.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.33.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.34.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.35.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.36.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.37.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.38.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.39.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.40.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.41.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.42.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.43.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.44.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.45.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.46.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.47.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.48.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.49.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.50.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.51.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.52.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.53.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.54.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.55.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.56.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.57.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.58.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.59.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.60.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.61.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.62.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.19.mlp.experts.63.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.0.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.1.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.2.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.3.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.4.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.5.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.6.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.7.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.8.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.9.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.10.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.11.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.12.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.13.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.14.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.15.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.16.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.17.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.18.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.19.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.20.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.21.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.22.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.23.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.24.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.25.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.26.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.27.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.28.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.29.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.30.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.31.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.32.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.33.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.34.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.35.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.36.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.37.down_proj.weight": "model-00015-of-00052.safetensors", - "model.layers.20.mlp.experts.38.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.39.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.40.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.41.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.42.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.43.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.44.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.45.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.46.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.47.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.48.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.49.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.50.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.51.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.52.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.53.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.54.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.55.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.56.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.57.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.58.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.59.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.60.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.61.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.62.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.20.mlp.experts.63.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.0.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.1.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.2.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.3.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.4.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.5.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.6.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.7.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.8.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.9.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.10.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.11.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.12.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.13.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.14.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.15.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.16.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.17.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.18.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.19.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.20.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.21.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.22.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.23.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.24.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.25.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.26.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.27.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.28.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.29.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.30.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.31.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.32.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.33.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.34.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.35.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.36.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.37.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.38.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.39.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.40.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.41.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.42.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.43.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.44.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.45.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.46.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.47.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.48.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.49.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.50.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.51.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.52.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.53.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.54.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.55.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.56.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.57.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.58.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.59.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.60.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.61.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.62.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.21.mlp.experts.63.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.0.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.1.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.2.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.3.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.4.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.5.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.6.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.7.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.8.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.9.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.10.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.11.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.12.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.13.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.14.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.15.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.16.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.17.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.18.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.19.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.20.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.21.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.22.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.23.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.24.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.25.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.26.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.27.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.28.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.29.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.30.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.31.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.32.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.33.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.34.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.35.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.36.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.37.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.38.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.39.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.40.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.41.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.42.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.43.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.44.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.45.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.46.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.47.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.48.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.49.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.50.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.51.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.52.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.53.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.54.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.55.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.56.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.57.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.58.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.59.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.60.down_proj.weight": "model-00016-of-00052.safetensors", - "model.layers.22.mlp.experts.61.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.22.mlp.experts.62.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.22.mlp.experts.63.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.0.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.1.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.2.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.3.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.4.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.5.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.6.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.7.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.8.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.9.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.10.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.11.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.12.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.13.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.14.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.15.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.16.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.17.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.18.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.19.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.20.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.21.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.22.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.23.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.24.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.25.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.26.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.27.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.28.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.29.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.30.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.31.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.32.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.33.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.34.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.35.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.36.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.37.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.38.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.39.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.40.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.41.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.42.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.43.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.44.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.45.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.46.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.47.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.48.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.49.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.50.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.51.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.52.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.53.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.54.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.55.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.56.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.57.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.58.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.59.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.60.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.61.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.62.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.23.mlp.experts.63.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.0.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.1.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.2.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.3.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.4.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.5.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.6.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.7.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.8.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.9.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.10.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.11.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.12.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.13.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.14.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.15.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.16.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.17.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.18.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.19.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.20.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.21.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.22.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.23.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.24.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.25.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.26.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.27.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.28.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.29.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.30.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.31.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.32.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.33.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.34.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.35.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.36.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.37.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.38.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.39.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.40.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.41.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.42.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.43.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.44.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.45.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.46.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.47.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.48.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.49.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.50.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.51.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.52.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.53.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.54.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.55.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.56.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.57.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.58.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.59.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.60.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.61.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.62.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.24.mlp.experts.63.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.0.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.1.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.2.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.3.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.4.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.5.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.6.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.7.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.8.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.9.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.10.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.11.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.12.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.13.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.14.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.15.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.16.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.17.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.18.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.19.down_proj.weight": "model-00017-of-00052.safetensors", - "model.layers.25.mlp.experts.20.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.21.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.22.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.23.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.24.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.25.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.26.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.27.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.28.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.29.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.30.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.31.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.32.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.33.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.34.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.35.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.36.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.37.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.38.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.39.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.40.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.41.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.42.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.43.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.44.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.45.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.46.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.47.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.48.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.49.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.50.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.51.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.52.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.53.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.54.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.55.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.56.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.57.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.58.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.59.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.60.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.61.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.62.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.25.mlp.experts.63.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.0.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.1.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.2.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.3.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.4.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.5.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.6.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.7.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.8.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.9.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.10.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.11.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.12.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.13.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.14.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.15.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.16.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.17.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.18.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.19.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.20.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.21.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.22.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.23.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.24.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.25.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.26.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.27.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.28.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.29.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.30.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.31.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.32.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.33.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.34.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.35.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.36.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.37.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.38.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.39.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.40.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.41.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.42.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.43.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.44.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.45.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.46.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.47.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.48.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.49.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.50.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.51.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.52.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.53.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.54.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.55.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.56.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.57.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.58.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.59.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.60.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.61.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.62.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.26.mlp.experts.63.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.0.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.1.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.2.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.3.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.4.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.5.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.6.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.7.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.8.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.9.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.10.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.11.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.12.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.13.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.14.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.15.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.16.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.17.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.18.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.19.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.20.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.21.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.22.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.23.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.24.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.25.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.26.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.27.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.28.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.29.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.30.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.31.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.32.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.33.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.34.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.35.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.36.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.37.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.38.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.39.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.40.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.41.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.42.down_proj.weight": "model-00018-of-00052.safetensors", - "model.layers.27.mlp.experts.43.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.44.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.45.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.46.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.47.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.48.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.49.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.50.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.51.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.52.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.53.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.54.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.55.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.56.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.57.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.58.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.59.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.60.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.61.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.62.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.27.mlp.experts.63.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.0.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.1.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.2.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.3.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.4.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.5.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.6.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.7.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.8.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.9.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.10.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.11.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.12.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.13.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.14.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.15.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.16.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.17.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.18.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.19.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.20.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.21.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.22.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.23.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.24.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.25.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.26.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.27.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.28.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.29.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.30.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.31.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.32.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.33.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.34.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.35.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.36.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.37.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.38.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.39.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.40.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.41.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.42.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.43.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.44.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.45.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.46.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.47.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.48.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.49.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.50.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.51.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.52.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.53.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.54.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.55.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.56.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.57.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.58.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.59.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.60.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.61.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.62.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.28.mlp.experts.63.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.0.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.1.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.2.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.3.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.4.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.5.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.6.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.7.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.8.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.9.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.10.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.11.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.12.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.13.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.14.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.15.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.16.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.17.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.18.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.19.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.20.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.21.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.22.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.23.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.24.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.25.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.26.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.27.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.28.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.29.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.30.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.31.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.32.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.33.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.34.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.35.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.36.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.37.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.38.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.39.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.40.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.41.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.42.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.43.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.44.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.45.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.46.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.47.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.48.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.49.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.50.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.51.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.52.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.53.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.54.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.55.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.56.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.57.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.58.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.59.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.60.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.61.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.62.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.29.mlp.experts.63.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.30.mlp.experts.0.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.30.mlp.experts.1.down_proj.weight": "model-00019-of-00052.safetensors", - "model.layers.30.mlp.experts.2.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.3.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.4.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.5.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.6.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.7.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.8.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.9.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.10.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.11.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.12.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.13.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.14.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.15.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.16.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.17.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.18.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.19.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.20.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.21.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.22.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.23.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.24.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.25.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.26.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.27.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.28.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.29.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.30.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.31.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.32.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.33.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.34.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.35.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.36.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.37.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.38.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.39.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.40.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.41.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.42.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.43.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.44.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.45.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.46.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.47.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.48.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.49.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.50.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.51.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.52.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.53.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.54.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.55.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.56.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.57.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.58.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.59.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.60.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.61.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.62.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.30.mlp.experts.63.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.0.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.1.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.2.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.3.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.4.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.5.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.6.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.7.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.8.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.9.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.10.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.11.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.12.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.13.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.14.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.15.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.16.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.17.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.18.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.19.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.20.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.21.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.22.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.23.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.24.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.25.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.26.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.27.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.28.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.29.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.30.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.31.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.32.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.33.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.34.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.35.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.36.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.37.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.38.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.39.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.40.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.41.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.42.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.43.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.44.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.45.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.46.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.47.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.48.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.49.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.50.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.51.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.52.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.53.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.54.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.55.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.56.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.57.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.58.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.59.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.60.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.61.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.62.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.31.mlp.experts.63.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.0.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.1.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.2.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.3.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.4.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.5.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.6.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.7.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.8.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.9.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.10.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.11.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.12.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.13.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.14.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.15.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.16.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.17.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.18.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.19.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.20.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.21.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.22.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.23.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.24.down_proj.weight": "model-00020-of-00052.safetensors", - "model.layers.32.mlp.experts.25.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.26.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.27.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.28.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.29.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.30.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.31.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.32.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.33.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.34.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.35.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.36.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.37.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.38.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.39.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.40.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.41.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.42.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.43.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.44.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.45.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.46.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.47.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.48.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.49.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.50.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.51.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.52.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.53.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.54.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.55.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.56.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.57.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.58.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.59.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.60.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.61.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.62.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.32.mlp.experts.63.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.0.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.1.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.2.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.3.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.4.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.5.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.6.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.7.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.8.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.9.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.10.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.11.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.12.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.13.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.14.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.15.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.16.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.17.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.18.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.19.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.20.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.21.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.22.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.23.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.24.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.25.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.26.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.27.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.28.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.29.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.30.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.31.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.32.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.33.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.34.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.35.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.36.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.37.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.38.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.39.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.40.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.41.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.42.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.43.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.44.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.45.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.46.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.47.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.48.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.49.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.50.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.51.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.52.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.53.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.54.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.55.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.56.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.57.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.58.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.59.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.60.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.61.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.62.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.33.mlp.experts.63.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.0.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.1.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.2.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.3.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.4.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.5.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.6.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.7.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.8.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.9.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.10.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.11.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.12.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.13.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.14.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.15.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.16.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.17.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.18.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.19.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.20.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.21.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.22.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.23.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.24.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.25.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.26.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.27.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.28.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.29.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.30.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.31.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.32.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.33.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.34.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.35.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.36.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.37.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.38.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.39.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.40.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.41.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.42.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.43.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.44.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.45.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.46.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.47.down_proj.weight": "model-00021-of-00052.safetensors", - "model.layers.34.mlp.experts.48.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.49.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.50.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.51.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.52.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.53.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.54.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.55.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.56.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.57.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.58.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.59.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.60.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.61.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.62.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.34.mlp.experts.63.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.0.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.1.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.2.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.3.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.4.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.5.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.6.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.7.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.8.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.9.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.10.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.11.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.12.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.13.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.14.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.15.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.16.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.17.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.18.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.19.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.20.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.21.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.22.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.23.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.24.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.25.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.26.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.27.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.28.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.29.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.30.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.31.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.32.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.33.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.34.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.35.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.36.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.37.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.38.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.39.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.40.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.41.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.42.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.43.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.44.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.45.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.46.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.47.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.48.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.49.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.50.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.51.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.52.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.53.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.54.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.55.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.56.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.57.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.58.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.59.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.60.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.61.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.62.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.35.mlp.experts.63.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.0.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.1.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.2.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.3.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.4.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.5.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.6.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.7.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.8.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.9.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.10.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.11.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.12.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.13.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.14.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.15.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.16.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.17.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.18.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.19.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.20.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.21.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.22.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.23.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.24.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.25.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.26.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.27.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.28.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.29.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.30.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.31.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.32.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.33.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.34.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.35.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.36.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.37.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.38.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.39.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.40.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.41.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.42.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.43.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.44.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.45.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.46.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.47.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.48.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.49.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.50.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.51.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.52.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.53.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.54.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.55.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.56.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.57.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.58.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.59.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.60.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.61.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.62.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.36.mlp.experts.63.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.37.mlp.experts.0.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.37.mlp.experts.1.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.37.mlp.experts.2.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.37.mlp.experts.3.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.37.mlp.experts.4.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.37.mlp.experts.5.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.37.mlp.experts.6.down_proj.weight": "model-00022-of-00052.safetensors", - "model.layers.37.mlp.experts.7.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.8.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.9.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.10.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.11.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.12.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.13.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.14.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.15.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.16.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.17.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.18.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.19.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.20.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.21.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.22.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.23.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.24.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.25.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.26.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.27.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.28.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.29.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.30.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.31.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.32.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.33.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.34.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.35.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.36.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.37.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.38.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.39.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.40.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.41.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.42.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.43.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.44.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.45.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.46.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.47.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.48.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.49.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.50.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.51.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.52.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.53.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.54.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.55.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.56.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.57.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.58.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.59.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.60.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.61.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.62.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.37.mlp.experts.63.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.0.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.1.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.2.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.3.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.4.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.5.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.6.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.7.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.8.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.9.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.10.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.11.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.12.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.13.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.14.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.15.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.16.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.17.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.18.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.19.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.20.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.21.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.22.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.23.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.24.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.25.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.26.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.27.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.28.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.29.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.30.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.31.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.32.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.33.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.34.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.35.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.36.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.37.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.38.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.39.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.40.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.41.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.42.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.43.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.44.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.45.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.46.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.47.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.48.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.49.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.50.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.51.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.52.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.53.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.54.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.55.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.56.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.57.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.58.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.59.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.60.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.61.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.62.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.38.mlp.experts.63.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.0.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.1.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.2.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.3.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.4.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.5.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.6.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.7.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.8.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.9.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.10.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.11.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.12.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.13.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.14.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.15.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.16.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.17.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.18.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.19.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.20.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.21.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.22.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.23.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.24.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.25.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.26.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.27.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.28.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.29.down_proj.weight": "model-00023-of-00052.safetensors", - "model.layers.39.mlp.experts.30.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.31.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.32.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.33.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.34.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.35.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.36.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.37.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.38.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.39.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.40.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.41.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.42.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.43.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.44.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.45.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.46.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.47.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.48.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.49.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.50.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.51.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.52.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.53.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.54.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.55.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.56.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.57.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.58.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.59.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.60.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.61.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.62.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.39.mlp.experts.63.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.0.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.1.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.2.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.3.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.4.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.5.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.6.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.7.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.8.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.9.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.10.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.11.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.12.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.13.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.14.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.15.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.16.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.17.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.18.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.19.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.20.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.21.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.22.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.23.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.24.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.25.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.26.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.27.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.28.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.29.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.30.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.31.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.32.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.33.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.34.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.35.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.36.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.37.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.38.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.39.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.40.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.41.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.42.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.43.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.44.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.45.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.46.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.47.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.48.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.49.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.50.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.51.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.52.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.53.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.54.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.55.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.56.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.57.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.58.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.59.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.60.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.61.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.62.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.40.mlp.experts.63.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.0.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.1.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.2.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.3.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.4.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.5.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.6.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.7.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.8.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.9.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.10.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.11.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.12.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.13.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.14.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.15.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.16.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.17.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.18.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.19.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.20.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.21.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.22.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.23.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.24.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.25.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.26.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.27.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.28.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.29.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.30.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.31.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.32.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.33.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.34.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.35.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.36.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.37.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.38.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.39.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.40.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.41.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.42.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.43.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.44.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.45.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.46.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.47.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.48.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.49.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.50.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.51.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.52.down_proj.weight": "model-00024-of-00052.safetensors", - "model.layers.41.mlp.experts.53.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.41.mlp.experts.54.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.41.mlp.experts.55.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.41.mlp.experts.56.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.41.mlp.experts.57.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.41.mlp.experts.58.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.41.mlp.experts.59.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.41.mlp.experts.60.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.41.mlp.experts.61.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.41.mlp.experts.62.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.41.mlp.experts.63.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.0.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.1.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.2.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.3.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.4.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.5.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.6.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.7.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.8.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.9.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.10.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.11.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.12.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.13.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.14.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.15.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.16.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.17.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.18.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.19.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.20.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.21.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.22.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.23.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.24.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.25.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.26.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.27.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.28.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.29.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.30.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.31.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.32.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.33.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.34.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.35.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.36.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.37.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.38.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.39.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.40.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.41.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.42.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.43.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.44.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.45.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.46.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.47.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.48.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.49.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.50.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.51.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.52.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.53.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.54.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.55.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.56.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.57.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.58.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.59.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.60.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.61.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.62.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.42.mlp.experts.63.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.0.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.1.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.2.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.3.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.4.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.5.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.6.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.7.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.8.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.9.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.10.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.11.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.12.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.13.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.14.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.15.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.16.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.17.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.18.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.19.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.20.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.21.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.22.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.23.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.24.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.25.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.26.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.27.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.28.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.29.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.30.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.31.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.32.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.33.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.34.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.35.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.36.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.37.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.38.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.39.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.40.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.41.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.42.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.43.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.44.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.45.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.46.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.47.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.48.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.49.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.50.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.51.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.52.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.53.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.54.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.55.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.56.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.57.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.58.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.59.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.60.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.61.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.62.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.43.mlp.experts.63.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.0.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.1.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.2.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.3.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.4.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.5.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.6.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.7.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.8.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.9.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.10.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.11.down_proj.weight": "model-00025-of-00052.safetensors", - "model.layers.44.mlp.experts.12.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.13.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.14.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.15.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.16.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.17.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.18.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.19.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.20.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.21.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.22.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.23.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.24.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.25.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.26.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.27.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.28.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.29.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.30.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.31.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.32.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.33.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.34.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.35.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.36.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.37.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.38.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.39.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.40.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.41.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.42.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.43.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.44.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.45.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.46.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.47.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.48.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.49.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.50.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.51.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.52.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.53.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.54.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.55.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.56.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.57.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.58.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.59.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.60.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.61.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.62.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.44.mlp.experts.63.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.0.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.1.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.2.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.3.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.4.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.5.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.6.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.7.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.8.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.9.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.10.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.11.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.12.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.13.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.14.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.15.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.16.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.17.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.18.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.19.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.20.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.21.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.22.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.23.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.24.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.25.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.26.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.27.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.28.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.29.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.30.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.31.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.32.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.33.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.34.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.35.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.36.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.37.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.38.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.39.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.40.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.41.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.42.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.43.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.44.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.45.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.46.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.47.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.48.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.49.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.50.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.51.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.52.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.53.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.54.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.55.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.56.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.57.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.58.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.59.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.60.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.61.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.62.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.45.mlp.experts.63.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.0.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.1.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.2.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.3.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.4.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.5.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.6.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.7.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.8.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.9.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.10.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.11.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.12.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.13.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.14.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.15.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.16.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.17.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.18.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.19.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.20.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.21.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.22.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.23.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.24.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.25.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.26.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.27.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.28.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.29.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.30.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.31.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.32.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.33.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.34.down_proj.weight": "model-00026-of-00052.safetensors", - "model.layers.46.mlp.experts.35.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.36.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.37.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.38.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.39.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.40.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.41.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.42.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.43.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.44.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.45.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.46.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.47.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.48.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.49.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.50.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.51.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.52.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.53.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.54.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.55.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.56.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.57.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.58.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.59.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.60.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.61.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.62.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.46.mlp.experts.63.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.0.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.1.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.2.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.3.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.4.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.5.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.6.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.7.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.8.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.9.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.10.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.11.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.12.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.13.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.14.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.15.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.16.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.17.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.18.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.19.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.20.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.21.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.22.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.23.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.24.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.25.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.26.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.27.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.28.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.29.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.30.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.31.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.32.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.33.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.34.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.35.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.36.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.37.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.38.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.39.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.40.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.41.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.42.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.43.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.44.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.45.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.46.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.47.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.48.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.49.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.50.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.51.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.52.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.53.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.54.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.55.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.56.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.57.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.58.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.59.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.60.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.61.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.62.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.47.mlp.experts.63.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.0.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.1.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.2.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.3.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.4.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.5.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.6.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.7.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.8.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.9.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.10.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.11.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.12.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.13.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.14.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.15.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.16.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.17.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.18.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.19.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.20.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.21.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.22.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.23.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.24.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.25.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.26.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.27.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.28.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.29.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.30.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.31.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.32.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.33.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.34.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.35.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.36.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.37.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.38.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.39.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.40.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.41.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.42.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.43.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.44.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.45.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.46.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.47.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.48.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.49.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.50.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.51.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.52.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.53.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.54.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.55.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.56.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.57.down_proj.weight": "model-00027-of-00052.safetensors", - "model.layers.48.mlp.experts.58.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.48.mlp.experts.59.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.48.mlp.experts.60.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.48.mlp.experts.61.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.48.mlp.experts.62.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.48.mlp.experts.63.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.0.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.1.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.2.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.3.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.4.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.5.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.6.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.7.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.8.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.9.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.10.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.11.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.12.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.13.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.14.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.15.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.16.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.17.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.18.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.19.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.20.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.21.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.22.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.23.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.24.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.25.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.26.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.27.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.28.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.29.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.30.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.31.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.32.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.33.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.34.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.35.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.36.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.37.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.38.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.39.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.40.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.41.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.42.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.43.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.44.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.45.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.46.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.47.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.48.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.49.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.50.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.51.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.52.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.53.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.54.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.55.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.56.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.57.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.58.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.59.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.60.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.61.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.62.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.49.mlp.experts.63.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.0.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.1.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.2.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.3.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.4.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.5.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.6.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.7.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.8.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.9.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.10.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.11.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.12.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.13.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.14.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.15.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.16.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.17.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.18.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.19.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.20.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.21.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.22.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.23.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.24.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.25.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.26.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.27.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.28.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.29.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.30.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.31.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.32.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.33.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.34.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.35.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.36.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.37.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.38.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.39.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.40.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.41.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.42.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.43.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.44.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.45.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.46.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.47.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.48.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.49.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.50.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.51.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.52.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.53.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.54.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.55.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.56.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.57.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.58.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.59.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.60.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.61.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.62.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.50.mlp.experts.63.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.0.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.1.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.2.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.3.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.4.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.5.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.6.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.7.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.8.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.9.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.10.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.11.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.12.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.13.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.14.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.15.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.16.down_proj.weight": "model-00028-of-00052.safetensors", - "model.layers.51.mlp.experts.17.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.18.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.19.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.20.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.21.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.22.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.23.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.24.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.25.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.26.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.27.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.28.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.29.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.30.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.31.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.32.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.33.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.34.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.35.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.36.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.37.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.38.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.39.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.40.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.41.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.42.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.43.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.44.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.45.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.46.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.47.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.48.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.49.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.50.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.51.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.52.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.53.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.54.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.55.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.56.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.57.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.58.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.59.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.60.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.61.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.62.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.51.mlp.experts.63.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.0.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.1.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.2.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.3.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.4.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.5.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.6.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.7.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.8.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.9.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.10.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.11.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.12.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.13.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.14.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.15.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.16.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.17.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.18.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.19.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.20.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.21.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.22.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.23.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.24.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.25.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.26.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.27.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.28.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.29.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.30.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.31.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.32.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.33.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.34.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.35.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.36.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.37.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.38.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.39.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.40.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.41.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.42.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.43.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.44.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.45.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.46.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.47.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.48.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.49.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.50.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.51.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.52.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.53.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.54.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.55.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.56.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.57.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.58.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.59.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.60.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.61.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.62.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.52.mlp.experts.63.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.0.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.1.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.2.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.3.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.4.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.5.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.6.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.7.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.8.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.9.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.10.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.11.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.12.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.13.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.14.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.15.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.16.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.17.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.18.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.19.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.20.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.21.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.22.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.23.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.24.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.25.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.26.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.27.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.28.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.29.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.30.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.31.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.32.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.33.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.34.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.35.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.36.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.37.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.38.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.39.down_proj.weight": "model-00029-of-00052.safetensors", - "model.layers.53.mlp.experts.40.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.41.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.42.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.43.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.44.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.45.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.46.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.47.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.48.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.49.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.50.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.51.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.52.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.53.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.54.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.55.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.56.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.57.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.58.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.59.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.60.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.61.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.62.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.53.mlp.experts.63.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.0.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.1.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.2.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.3.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.4.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.5.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.6.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.7.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.8.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.9.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.10.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.11.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.12.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.13.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.14.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.15.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.16.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.17.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.18.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.19.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.20.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.21.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.22.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.23.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.24.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.25.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.26.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.27.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.28.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.29.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.30.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.31.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.32.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.33.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.34.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.35.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.36.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.37.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.38.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.39.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.40.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.41.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.42.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.43.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.44.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.45.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.46.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.47.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.48.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.49.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.50.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.51.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.52.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.53.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.54.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.55.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.56.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.57.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.58.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.59.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.60.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.61.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.62.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.54.mlp.experts.63.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.0.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.1.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.2.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.3.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.4.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.5.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.6.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.7.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.8.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.9.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.10.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.11.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.12.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.13.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.14.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.15.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.16.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.17.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.18.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.19.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.20.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.21.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.22.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.23.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.24.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.25.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.26.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.27.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.28.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.29.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.30.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.31.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.32.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.33.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.34.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.35.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.36.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.37.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.38.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.39.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.40.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.41.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.42.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.43.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.44.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.45.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.46.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.47.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.48.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.49.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.50.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.51.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.52.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.53.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.54.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.55.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.56.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.57.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.58.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.59.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.60.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.61.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.62.down_proj.weight": "model-00030-of-00052.safetensors", - "model.layers.55.mlp.experts.63.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.0.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.1.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.2.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.3.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.4.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.5.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.6.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.7.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.8.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.9.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.10.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.11.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.12.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.13.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.14.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.15.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.16.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.17.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.18.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.19.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.20.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.21.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.22.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.23.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.24.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.25.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.26.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.27.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.28.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.29.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.30.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.31.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.32.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.33.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.34.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.35.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.36.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.37.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.38.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.39.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.40.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.41.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.42.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.43.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.44.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.45.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.46.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.47.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.48.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.49.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.50.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.51.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.52.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.53.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.54.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.55.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.56.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.57.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.58.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.59.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.60.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.61.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.62.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.56.mlp.experts.63.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.0.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.1.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.2.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.3.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.4.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.5.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.6.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.7.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.8.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.9.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.10.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.11.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.12.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.13.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.14.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.15.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.16.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.17.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.18.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.19.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.20.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.21.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.22.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.23.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.24.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.25.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.26.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.27.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.28.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.29.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.30.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.31.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.32.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.33.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.34.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.35.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.36.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.37.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.38.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.39.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.40.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.41.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.42.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.43.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.44.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.45.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.46.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.47.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.48.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.49.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.50.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.51.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.52.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.53.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.54.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.55.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.56.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.57.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.58.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.59.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.60.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.61.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.62.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.57.mlp.experts.63.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.0.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.1.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.2.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.3.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.4.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.5.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.6.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.7.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.8.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.9.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.10.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.11.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.12.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.13.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.14.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.15.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.16.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.17.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.18.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.19.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.20.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.21.down_proj.weight": "model-00031-of-00052.safetensors", - "model.layers.58.mlp.experts.22.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.23.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.24.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.25.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.26.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.27.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.28.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.29.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.30.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.31.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.32.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.33.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.34.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.35.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.36.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.37.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.38.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.39.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.40.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.41.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.42.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.43.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.44.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.45.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.46.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.47.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.48.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.49.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.50.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.51.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.52.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.53.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.54.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.55.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.56.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.57.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.58.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.59.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.60.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.61.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.62.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.58.mlp.experts.63.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.0.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.1.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.2.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.3.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.4.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.5.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.6.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.7.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.8.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.9.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.10.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.11.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.12.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.13.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.14.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.15.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.16.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.17.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.18.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.19.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.20.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.21.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.22.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.23.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.24.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.25.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.26.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.27.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.28.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.29.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.30.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.31.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.32.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.33.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.34.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.35.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.36.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.37.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.38.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.39.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.40.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.41.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.42.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.43.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.44.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.45.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.46.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.47.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.48.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.49.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.50.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.51.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.52.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.53.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.54.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.55.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.56.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.57.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.58.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.59.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.60.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.61.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.62.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.59.mlp.experts.63.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.0.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.1.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.2.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.3.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.4.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.5.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.6.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.7.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.8.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.9.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.10.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.11.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.12.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.13.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.14.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.15.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.16.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.17.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.18.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.19.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.20.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.21.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.22.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.23.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.24.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.25.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.26.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.27.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.28.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.29.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.30.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.31.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.32.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.33.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.34.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.35.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.36.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.37.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.38.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.39.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.40.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.41.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.42.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.43.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.44.down_proj.weight": "model-00032-of-00052.safetensors", - "model.layers.60.mlp.experts.45.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.46.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.47.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.48.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.49.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.50.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.51.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.52.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.53.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.54.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.55.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.56.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.57.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.58.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.59.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.60.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.61.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.62.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.60.mlp.experts.63.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.0.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.1.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.2.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.3.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.4.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.5.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.6.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.7.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.8.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.9.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.10.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.11.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.12.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.13.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.14.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.15.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.16.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.17.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.18.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.19.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.20.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.21.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.22.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.23.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.24.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.25.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.26.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.27.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.28.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.29.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.30.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.31.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.32.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.33.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.34.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.35.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.36.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.37.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.38.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.39.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.40.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.41.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.42.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.43.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.44.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.45.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.46.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.47.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.48.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.49.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.50.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.51.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.52.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.53.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.54.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.55.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.56.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.57.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.58.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.59.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.60.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.61.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.62.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.61.mlp.experts.63.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.0.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.1.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.2.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.3.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.4.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.5.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.6.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.7.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.8.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.9.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.10.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.11.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.12.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.13.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.14.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.15.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.16.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.17.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.18.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.19.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.20.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.21.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.22.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.23.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.24.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.25.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.26.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.27.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.28.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.29.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.30.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.31.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.32.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.33.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.34.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.35.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.36.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.37.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.38.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.39.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.40.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.41.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.42.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.43.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.44.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.45.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.46.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.47.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.48.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.49.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.50.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.51.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.52.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.53.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.54.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.55.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.56.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.57.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.58.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.59.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.60.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.61.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.62.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.62.mlp.experts.63.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.63.mlp.experts.0.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.63.mlp.experts.1.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.63.mlp.experts.2.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.63.mlp.experts.3.down_proj.weight": "model-00033-of-00052.safetensors", - "model.layers.63.mlp.experts.4.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.5.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.6.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.7.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.8.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.9.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.10.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.11.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.12.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.13.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.14.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.15.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.16.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.17.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.18.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.19.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.20.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.21.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.22.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.23.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.24.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.25.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.26.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.27.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.28.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.29.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.30.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.31.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.32.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.33.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.34.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.35.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.36.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.37.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.38.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.39.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.40.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.41.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.42.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.43.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.44.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.45.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.46.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.47.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.48.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.49.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.50.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.51.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.52.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.53.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.54.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.55.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.56.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.57.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.58.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.59.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.60.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.61.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.62.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.63.mlp.experts.63.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.0.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.1.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.2.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.3.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.4.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.5.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.6.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.7.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.8.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.9.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.10.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.11.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.12.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.13.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.14.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.15.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.16.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.17.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.18.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.19.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.20.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.21.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.22.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.23.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.24.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.25.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.26.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.27.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.28.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.29.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.30.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.31.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.32.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.33.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.34.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.35.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.36.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.37.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.38.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.39.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.40.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.41.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.42.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.43.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.44.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.45.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.46.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.47.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.48.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.49.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.50.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.51.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.52.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.53.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.54.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.55.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.56.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.57.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.58.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.59.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.60.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.61.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.62.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.64.mlp.experts.63.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.0.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.1.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.2.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.3.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.4.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.5.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.6.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.7.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.8.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.9.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.10.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.11.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.12.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.13.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.14.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.15.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.16.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.17.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.18.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.19.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.20.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.21.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.22.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.23.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.24.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.25.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.26.down_proj.weight": "model-00034-of-00052.safetensors", - "model.layers.65.mlp.experts.27.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.28.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.29.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.30.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.31.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.32.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.33.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.34.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.35.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.36.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.37.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.38.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.39.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.40.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.41.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.42.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.43.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.44.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.45.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.46.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.47.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.48.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.49.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.50.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.51.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.52.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.53.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.54.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.55.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.56.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.57.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.58.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.59.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.60.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.61.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.62.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.65.mlp.experts.63.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.0.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.1.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.2.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.3.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.4.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.5.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.6.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.7.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.8.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.9.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.10.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.11.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.12.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.13.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.14.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.15.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.16.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.17.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.18.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.19.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.20.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.21.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.22.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.23.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.24.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.25.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.26.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.27.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.28.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.29.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.30.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.31.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.32.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.33.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.34.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.35.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.36.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.37.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.38.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.39.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.40.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.41.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.42.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.43.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.44.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.45.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.46.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.47.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.48.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.49.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.50.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.51.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.52.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.53.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.54.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.55.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.56.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.57.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.58.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.59.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.60.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.61.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.62.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.66.mlp.experts.63.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.0.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.1.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.2.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.3.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.4.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.5.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.6.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.7.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.8.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.9.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.10.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.11.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.12.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.13.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.14.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.15.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.16.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.17.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.18.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.19.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.20.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.21.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.22.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.23.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.24.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.25.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.26.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.27.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.28.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.29.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.30.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.31.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.32.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.33.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.34.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.35.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.36.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.37.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.38.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.39.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.40.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.41.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.42.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.43.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.44.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.45.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.46.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.47.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.48.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.49.down_proj.weight": "model-00035-of-00052.safetensors", - "model.layers.67.mlp.experts.50.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.51.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.52.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.53.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.54.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.55.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.56.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.57.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.58.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.59.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.60.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.61.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.62.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.67.mlp.experts.63.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.0.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.1.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.2.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.3.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.4.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.5.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.6.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.7.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.8.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.9.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.10.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.11.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.12.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.13.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.14.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.15.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.16.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.17.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.18.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.19.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.20.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.21.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.22.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.23.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.24.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.25.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.26.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.27.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.28.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.29.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.30.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.31.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.32.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.33.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.34.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.35.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.36.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.37.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.38.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.39.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.40.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.41.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.42.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.43.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.44.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.45.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.46.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.47.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.48.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.49.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.50.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.51.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.52.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.53.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.54.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.55.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.56.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.57.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.58.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.59.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.60.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.61.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.62.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.68.mlp.experts.63.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.0.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.1.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.2.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.3.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.4.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.5.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.6.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.7.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.8.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.9.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.10.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.11.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.12.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.13.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.14.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.15.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.16.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.17.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.18.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.19.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.20.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.21.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.22.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.23.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.24.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.25.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.26.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.27.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.28.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.29.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.30.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.31.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.32.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.33.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.34.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.35.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.36.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.37.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.38.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.39.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.40.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.41.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.42.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.43.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.44.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.45.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.46.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.47.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.48.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.49.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.50.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.51.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.52.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.53.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.54.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.55.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.56.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.57.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.58.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.59.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.60.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.61.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.62.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.69.mlp.experts.63.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.70.mlp.experts.0.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.70.mlp.experts.1.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.70.mlp.experts.2.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.70.mlp.experts.3.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.70.mlp.experts.4.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.70.mlp.experts.5.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.70.mlp.experts.6.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.70.mlp.experts.7.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.70.mlp.experts.8.down_proj.weight": "model-00036-of-00052.safetensors", - "model.layers.70.mlp.experts.9.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.10.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.11.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.12.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.13.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.14.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.15.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.16.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.17.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.18.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.19.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.20.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.21.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.22.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.23.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.24.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.25.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.26.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.27.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.28.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.29.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.30.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.31.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.32.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.33.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.34.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.35.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.36.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.37.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.38.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.39.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.40.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.41.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.42.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.43.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.44.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.45.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.46.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.47.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.48.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.49.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.50.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.51.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.52.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.53.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.54.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.55.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.56.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.57.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.58.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.59.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.60.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.61.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.62.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.70.mlp.experts.63.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.0.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.1.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.2.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.3.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.4.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.5.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.6.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.7.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.8.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.9.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.10.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.11.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.12.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.13.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.14.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.15.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.16.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.17.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.18.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.19.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.20.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.21.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.22.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.23.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.24.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.25.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.26.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.27.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.28.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.29.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.30.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.31.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.32.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.33.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.34.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.35.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.36.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.37.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.38.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.39.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.40.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.41.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.42.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.43.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.44.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.45.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.46.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.47.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.48.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.49.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.50.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.51.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.52.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.53.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.54.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.55.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.56.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.57.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.58.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.59.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.60.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.61.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.62.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.71.mlp.experts.63.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.0.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.1.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.2.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.3.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.4.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.5.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.6.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.7.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.8.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.9.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.10.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.11.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.12.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.13.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.14.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.15.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.16.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.17.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.18.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.19.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.20.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.21.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.22.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.23.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.24.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.25.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.26.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.27.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.28.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.29.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.30.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.31.down_proj.weight": "model-00037-of-00052.safetensors", - "model.layers.72.mlp.experts.32.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.33.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.34.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.35.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.36.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.37.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.38.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.39.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.40.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.41.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.42.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.43.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.44.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.45.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.46.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.47.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.48.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.49.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.50.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.51.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.52.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.53.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.54.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.55.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.56.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.57.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.58.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.59.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.60.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.61.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.62.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.72.mlp.experts.63.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.0.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.1.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.2.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.3.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.4.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.5.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.6.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.7.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.8.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.9.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.10.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.11.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.12.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.13.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.14.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.15.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.16.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.17.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.18.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.19.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.20.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.21.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.22.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.23.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.24.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.25.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.26.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.27.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.28.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.29.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.30.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.31.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.32.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.33.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.34.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.35.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.36.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.37.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.38.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.39.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.40.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.41.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.42.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.43.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.44.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.45.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.46.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.47.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.48.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.49.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.50.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.51.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.52.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.53.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.54.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.55.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.56.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.57.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.58.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.59.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.60.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.61.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.62.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.73.mlp.experts.63.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.0.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.1.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.2.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.3.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.4.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.5.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.6.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.7.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.8.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.9.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.10.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.11.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.12.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.13.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.14.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.15.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.16.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.17.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.18.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.19.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.20.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.21.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.22.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.23.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.24.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.25.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.26.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.27.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.28.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.29.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.30.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.31.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.32.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.33.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.34.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.35.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.36.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.37.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.38.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.39.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.40.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.41.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.42.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.43.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.44.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.45.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.46.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.47.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.48.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.49.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.50.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.51.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.52.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.53.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.54.down_proj.weight": "model-00038-of-00052.safetensors", - "model.layers.74.mlp.experts.55.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.74.mlp.experts.56.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.74.mlp.experts.57.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.74.mlp.experts.58.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.74.mlp.experts.59.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.74.mlp.experts.60.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.74.mlp.experts.61.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.74.mlp.experts.62.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.74.mlp.experts.63.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.0.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.1.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.2.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.3.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.4.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.5.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.6.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.7.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.8.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.9.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.10.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.11.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.12.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.13.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.14.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.15.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.16.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.17.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.18.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.19.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.20.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.21.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.22.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.23.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.24.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.25.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.26.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.27.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.28.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.29.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.30.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.31.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.32.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.33.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.34.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.35.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.36.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.37.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.38.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.39.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.40.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.41.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.42.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.43.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.44.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.45.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.46.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.47.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.48.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.49.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.50.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.51.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.52.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.53.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.54.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.55.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.56.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.57.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.58.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.59.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.60.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.61.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.62.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.75.mlp.experts.63.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.0.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.1.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.2.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.3.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.4.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.5.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.6.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.7.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.8.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.9.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.10.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.11.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.12.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.13.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.14.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.15.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.16.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.17.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.18.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.19.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.20.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.21.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.22.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.23.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.24.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.25.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.26.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.27.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.28.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.29.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.30.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.31.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.32.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.33.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.34.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.35.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.36.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.37.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.38.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.39.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.40.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.41.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.42.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.43.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.44.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.45.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.46.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.47.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.48.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.49.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.50.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.51.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.52.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.53.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.54.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.55.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.56.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.57.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.58.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.59.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.60.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.61.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.62.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.76.mlp.experts.63.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.0.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.1.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.2.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.3.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.4.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.5.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.6.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.7.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.8.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.9.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.10.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.11.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.12.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.13.down_proj.weight": "model-00039-of-00052.safetensors", - "model.layers.77.mlp.experts.14.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.15.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.16.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.17.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.18.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.19.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.20.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.21.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.22.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.23.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.24.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.25.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.26.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.27.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.28.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.29.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.30.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.31.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.32.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.33.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.34.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.35.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.36.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.37.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.38.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.39.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.40.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.41.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.42.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.43.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.44.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.45.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.46.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.47.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.48.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.49.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.50.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.51.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.52.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.53.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.54.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.55.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.56.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.57.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.58.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.59.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.60.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.61.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.62.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.77.mlp.experts.63.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.0.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.1.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.2.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.3.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.4.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.5.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.6.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.7.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.8.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.9.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.10.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.11.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.12.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.13.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.14.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.15.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.16.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.17.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.18.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.19.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.20.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.21.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.22.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.23.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.24.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.25.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.26.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.27.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.28.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.29.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.30.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.31.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.32.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.33.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.34.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.35.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.36.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.37.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.38.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.39.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.40.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.41.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.42.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.43.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.44.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.45.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.46.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.47.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.48.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.49.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.50.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.51.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.52.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.53.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.54.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.55.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.56.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.57.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.58.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.59.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.60.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.61.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.62.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.78.mlp.experts.63.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.0.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.1.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.2.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.3.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.4.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.5.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.6.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.7.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.8.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.9.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.10.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.11.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.12.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.13.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.14.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.15.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.16.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.17.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.18.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.19.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.20.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.21.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.22.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.23.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.24.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.25.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.26.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.27.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.28.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.29.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.30.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.31.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.32.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.33.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.34.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.35.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.36.down_proj.weight": "model-00040-of-00052.safetensors", - "model.layers.79.mlp.experts.37.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.38.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.39.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.40.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.41.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.42.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.43.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.44.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.45.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.46.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.47.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.48.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.49.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.50.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.51.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.52.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.53.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.54.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.55.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.56.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.57.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.58.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.59.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.60.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.61.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.62.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.79.mlp.experts.63.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.0.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.1.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.2.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.3.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.4.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.5.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.6.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.7.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.8.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.9.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.10.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.11.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.12.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.13.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.14.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.15.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.16.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.17.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.18.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.19.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.20.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.21.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.22.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.23.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.24.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.25.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.26.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.27.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.28.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.29.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.30.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.31.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.32.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.33.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.34.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.35.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.36.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.37.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.38.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.39.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.40.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.41.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.42.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.43.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.44.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.45.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.46.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.47.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.48.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.49.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.50.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.51.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.52.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.53.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.54.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.55.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.56.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.57.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.58.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.59.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.60.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.61.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.62.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.80.mlp.experts.63.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.0.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.1.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.2.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.3.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.4.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.5.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.6.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.7.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.8.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.9.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.10.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.11.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.12.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.13.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.14.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.15.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.16.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.17.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.18.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.19.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.20.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.21.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.22.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.23.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.24.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.25.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.26.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.27.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.28.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.29.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.30.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.31.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.32.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.33.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.34.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.35.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.36.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.37.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.38.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.39.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.40.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.41.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.42.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.43.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.44.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.45.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.46.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.47.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.48.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.49.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.50.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.51.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.52.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.53.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.54.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.55.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.56.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.57.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.58.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.59.down_proj.weight": "model-00041-of-00052.safetensors", - "model.layers.81.mlp.experts.60.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.81.mlp.experts.61.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.81.mlp.experts.62.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.81.mlp.experts.63.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.0.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.1.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.2.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.3.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.4.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.5.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.6.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.7.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.8.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.9.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.10.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.11.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.12.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.13.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.14.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.15.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.16.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.17.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.18.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.19.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.20.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.21.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.22.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.23.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.24.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.25.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.26.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.27.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.28.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.29.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.30.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.31.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.32.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.33.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.34.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.35.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.36.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.37.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.38.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.39.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.40.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.41.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.42.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.43.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.44.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.45.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.46.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.47.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.48.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.49.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.50.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.51.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.52.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.53.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.54.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.55.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.56.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.57.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.58.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.59.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.60.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.61.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.62.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.82.mlp.experts.63.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.0.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.1.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.2.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.3.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.4.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.5.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.6.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.7.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.8.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.9.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.10.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.11.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.12.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.13.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.14.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.15.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.16.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.17.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.18.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.19.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.20.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.21.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.22.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.23.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.24.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.25.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.26.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.27.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.28.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.29.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.30.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.31.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.32.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.33.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.34.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.35.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.36.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.37.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.38.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.39.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.40.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.41.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.42.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.43.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.44.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.45.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.46.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.47.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.48.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.49.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.50.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.51.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.52.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.53.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.54.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.55.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.56.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.57.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.58.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.59.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.60.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.61.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.62.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.83.mlp.experts.63.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.0.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.1.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.2.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.3.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.4.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.5.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.6.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.7.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.8.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.9.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.10.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.11.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.12.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.13.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.14.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.15.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.16.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.17.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.18.down_proj.weight": "model-00042-of-00052.safetensors", - "model.layers.84.mlp.experts.19.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.20.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.21.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.22.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.23.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.24.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.25.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.26.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.27.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.28.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.29.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.30.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.31.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.32.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.33.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.34.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.35.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.36.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.37.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.38.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.39.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.40.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.41.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.42.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.43.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.44.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.45.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.46.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.47.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.48.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.49.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.50.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.51.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.52.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.53.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.54.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.55.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.56.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.57.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.58.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.59.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.60.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.61.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.62.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.84.mlp.experts.63.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.0.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.1.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.2.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.3.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.4.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.5.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.6.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.7.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.8.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.9.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.10.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.11.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.12.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.13.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.14.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.15.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.16.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.17.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.18.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.19.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.20.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.21.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.22.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.23.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.24.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.25.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.26.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.27.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.28.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.29.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.30.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.31.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.32.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.33.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.34.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.35.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.36.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.37.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.38.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.39.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.40.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.41.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.42.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.43.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.44.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.45.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.46.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.47.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.48.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.49.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.50.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.51.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.52.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.53.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.54.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.55.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.56.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.57.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.58.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.59.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.60.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.61.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.62.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.85.mlp.experts.63.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.0.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.1.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.2.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.3.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.4.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.5.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.6.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.7.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.8.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.9.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.10.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.11.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.12.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.13.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.14.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.15.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.16.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.17.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.18.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.19.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.20.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.21.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.22.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.23.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.24.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.25.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.26.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.27.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.28.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.29.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.30.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.31.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.32.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.33.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.34.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.35.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.36.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.37.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.38.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.39.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.40.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.41.down_proj.weight": "model-00043-of-00052.safetensors", - "model.layers.86.mlp.experts.42.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.43.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.44.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.45.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.46.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.47.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.48.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.49.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.50.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.51.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.52.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.53.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.54.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.55.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.56.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.57.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.58.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.59.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.60.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.61.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.62.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.86.mlp.experts.63.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.0.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.1.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.2.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.3.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.4.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.5.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.6.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.7.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.8.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.9.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.10.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.11.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.12.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.13.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.14.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.15.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.16.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.17.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.18.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.19.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.20.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.21.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.22.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.23.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.24.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.25.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.26.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.27.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.28.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.29.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.30.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.31.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.32.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.33.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.34.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.35.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.36.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.37.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.38.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.39.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.40.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.41.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.42.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.43.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.44.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.45.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.46.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.47.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.48.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.49.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.50.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.51.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.52.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.53.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.54.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.55.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.56.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.57.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.58.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.59.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.60.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.61.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.62.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.87.mlp.experts.63.down_proj.weight": "model-00044-of-00052.safetensors", - "model.layers.0.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.1.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.2.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.3.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.4.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.5.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.6.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.7.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.8.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.9.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.10.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.11.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.12.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.13.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.14.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.15.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.16.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.17.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.18.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.19.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.20.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.21.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.22.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.23.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.24.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.25.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.26.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.27.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.28.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.29.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.30.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.31.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.32.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.33.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.34.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.35.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.36.attention.dense.weight": "model-00044-of-00052.safetensors", - "model.layers.37.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.38.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.39.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.40.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.41.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.42.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.43.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.44.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.45.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.46.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.47.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.48.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.49.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.50.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.51.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.52.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.53.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.54.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.55.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.56.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.57.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.58.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.59.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.60.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.61.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.62.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.63.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.64.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.65.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.66.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.67.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.68.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.69.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.70.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.71.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.72.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.73.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.74.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.75.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.76.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.77.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.78.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.79.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.80.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.81.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.82.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.83.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.84.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.85.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.86.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.layers.87.attention.dense.weight": "model-00045-of-00052.safetensors", - "model.norm.weight": "model-00045-of-00052.safetensors", - "lm_head.weight": "model-00045-of-00052.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.0.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.1.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.2.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.3.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.4.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.5.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.6.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.7.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.8.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.9.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.10.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.11.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.12.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.13.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.14.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.15.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.16.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.17.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.18.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.19.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.20.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.21.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.22.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.23.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.24.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.25.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.26.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.27.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.28.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.29.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.30.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.31.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.32.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.32.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.33.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.33.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.34.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.34.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.35.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.35.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.36.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.36.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.37.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.37.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.38.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.38.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.39.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.39.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.40.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.40.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.41.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.41.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.42.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.42.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.43.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.43.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.44.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.44.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.45.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.45.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.46.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.46.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.47.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.47.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.48.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.48.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.49.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.49.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.50.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.50.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.51.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.51.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.52.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.52.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.53.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.53.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.54.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.54.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.55.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.55.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.56.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.56.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.57.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.57.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.58.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.58.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.59.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.59.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.60.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.60.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.61.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.61.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.62.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.62.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.63.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.63.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.64.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.64.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.65.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.65.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.66.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.66.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.67.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.67.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.68.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.68.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.69.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.69.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.70.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.70.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.71.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.71.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.72.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.72.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.73.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.73.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.74.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.74.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.75.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.75.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.76.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.76.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.77.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.77.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.78.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.78.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.79.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.79.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.80.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.80.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.81.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.81.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.82.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.82.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.83.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.83.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.84.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.84.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.85.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.85.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.86.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.86.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.87.post_attention_layernorm.weight": "model-00045-of-00052.safetensors", - "model.layers.87.mlp.gate.weight": "model-00045-of-00052.safetensors", - "model.layers.0.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00045-of-00052.safetensors", - "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.48.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.49.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.50.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.51.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.52.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.53.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.54.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.55.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.56.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.57.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.58.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.59.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.60.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.61.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.62.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.63.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.64.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.65.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.66.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.67.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.68.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.69.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.70.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.71.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.72.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.73.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.74.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.75.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.76.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.77.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.78.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.79.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.80.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.81.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.82.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.83.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.84.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.85.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.86.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.87.mlp.shared_experts.gate_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.16.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.17.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.18.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.19.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.20.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.21.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.22.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.23.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.24.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.25.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.26.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.27.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.28.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.29.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.30.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.31.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.32.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.33.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.34.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.35.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.36.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.37.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.38.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.39.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.40.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.41.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.42.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.43.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.44.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.45.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.46.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.47.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.48.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.49.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.50.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.51.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.52.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.53.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.54.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.55.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.56.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.57.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.58.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.59.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.60.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.61.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.62.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.0.mlp.experts.63.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.16.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.17.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.18.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.19.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.20.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.21.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.22.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.23.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.24.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.25.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.26.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.27.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.28.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.29.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.30.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.31.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.32.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.33.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.34.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.35.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.36.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.37.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.38.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.39.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.40.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.41.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.42.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.43.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.44.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.45.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.46.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.47.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.48.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.49.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.50.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.51.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.52.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.53.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.54.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.55.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.56.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.57.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.58.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.59.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.60.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.61.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.62.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.1.mlp.experts.63.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.16.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.17.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.18.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.19.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.20.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.21.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.22.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.23.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.24.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.25.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.26.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.27.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.28.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.29.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.30.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.31.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.32.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.33.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.34.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.35.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.36.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.37.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.38.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.39.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.40.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.41.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.42.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.43.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.44.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.45.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.46.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.47.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.48.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.49.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.50.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.51.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.52.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.53.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.54.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.55.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.56.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.57.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.58.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.59.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.60.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.61.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.62.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.2.mlp.experts.63.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.16.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.17.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.18.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.19.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.20.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.21.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.22.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.23.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.24.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.25.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.26.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.27.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.28.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.29.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.30.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.31.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.32.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.33.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.34.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.35.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.36.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.37.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.38.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.39.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.40.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.41.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.42.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.43.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.44.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.45.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.46.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.47.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.48.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.49.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.50.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.51.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.52.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.53.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.54.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.55.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.56.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.57.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.58.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.59.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.60.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.61.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.62.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.3.mlp.experts.63.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.16.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.17.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.18.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.19.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.20.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.21.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.22.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.23.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.24.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.25.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.26.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.27.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.28.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.29.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.30.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.31.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.32.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.33.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.34.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.35.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.36.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.37.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.38.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.39.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.40.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.41.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.42.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.43.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.44.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.45.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.46.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.47.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.48.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.49.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.50.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.51.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.52.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.53.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.54.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.55.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.56.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.57.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.58.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.59.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.60.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.61.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.62.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.4.mlp.experts.63.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.16.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.17.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.18.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.19.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.20.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.21.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.22.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.23.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.24.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.25.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.26.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.27.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.28.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.29.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.30.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.31.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.32.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.33.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.34.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.35.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.36.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.37.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.38.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.39.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.40.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.41.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.42.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.43.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.44.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.45.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.46.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.47.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.48.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.49.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.50.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.51.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.52.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.53.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.54.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.55.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.56.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.57.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.58.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.59.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.60.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.61.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.62.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.5.mlp.experts.63.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.16.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.17.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.18.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.19.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.20.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.21.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.22.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.23.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.24.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.25.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.26.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.27.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.28.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.29.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.30.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.31.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.32.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.33.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.34.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.35.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.36.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.37.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.38.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.39.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.40.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.41.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.42.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.43.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.44.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.45.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.46.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.47.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.48.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.49.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.50.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.51.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.52.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.53.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.54.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.55.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.56.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.57.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.58.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.59.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.60.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.61.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.62.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.6.mlp.experts.63.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.16.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.17.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.18.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.19.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.20.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.21.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.22.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.23.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.24.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.25.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.26.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.27.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.28.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.29.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.30.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.31.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.32.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.33.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.34.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.35.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.36.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.37.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.38.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.39.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.40.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.41.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.42.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.43.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.44.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.45.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.46.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.47.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.48.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.49.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.50.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.51.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.52.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.53.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.54.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.55.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.56.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.57.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.58.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.59.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.60.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.61.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.62.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.7.mlp.experts.63.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.16.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.17.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.18.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.19.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.20.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.21.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.22.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.23.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.24.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.25.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.26.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.27.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.28.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.29.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.30.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.31.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.32.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.33.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.34.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.35.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.36.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.37.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.38.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.39.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.40.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.41.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.42.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.43.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.44.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.45.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.46.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.47.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.48.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.49.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.50.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.51.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.52.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.53.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.54.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.55.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.56.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.57.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.58.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.59.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.60.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.61.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.62.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.8.mlp.experts.63.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.16.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.17.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.18.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.19.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.20.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.21.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.22.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.23.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.24.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.25.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.26.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.27.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.28.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.29.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.30.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.31.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.32.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.33.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.34.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.35.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.36.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.37.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.38.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.39.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.40.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.41.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.42.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.43.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.44.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.45.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.46.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.47.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.48.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.49.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.50.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.51.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.52.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.53.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.54.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.55.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.56.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.57.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.58.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.59.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.60.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.61.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.62.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.9.mlp.experts.63.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.0.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.1.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.2.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.3.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.4.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.5.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.6.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.7.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.8.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.9.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.10.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.11.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.12.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.13.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.14.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.15.up_proj.weight": "model-00046-of-00052.safetensors", - "model.layers.10.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.10.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.11.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.12.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.13.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.14.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.15.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.16.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.17.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.18.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.19.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.20.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.21.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.22.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.23.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.24.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.25.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.26.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.27.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.8.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.9.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.10.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.11.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.12.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.13.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.14.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.15.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.16.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.17.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.18.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.19.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.20.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.21.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.22.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.23.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.24.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.25.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.26.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.27.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.28.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.29.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.30.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.31.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.32.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.33.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.34.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.35.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.36.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.37.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.38.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.39.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.40.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.41.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.42.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.43.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.44.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.45.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.46.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.47.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.48.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.49.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.50.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.51.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.52.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.53.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.54.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.55.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.56.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.57.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.58.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.59.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.60.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.61.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.62.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.28.mlp.experts.63.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.29.mlp.experts.0.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.29.mlp.experts.1.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.29.mlp.experts.2.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.29.mlp.experts.3.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.29.mlp.experts.4.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.29.mlp.experts.5.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.29.mlp.experts.6.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.29.mlp.experts.7.up_proj.weight": "model-00047-of-00052.safetensors", - "model.layers.29.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.29.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.30.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.31.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.32.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.33.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.34.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.35.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.36.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.37.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.38.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.39.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.40.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.41.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.42.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.43.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.44.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.45.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.46.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.0.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.1.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.2.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.3.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.4.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.5.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.6.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.7.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.8.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.9.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.10.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.11.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.12.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.13.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.14.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.15.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.16.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.17.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.18.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.19.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.20.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.21.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.22.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.23.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.24.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.25.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.26.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.27.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.28.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.29.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.30.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.31.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.32.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.33.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.34.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.35.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.36.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.37.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.38.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.39.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.40.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.41.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.42.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.43.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.44.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.45.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.46.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.47.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.48.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.49.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.50.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.51.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.52.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.53.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.54.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.55.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.56.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.57.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.58.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.59.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.60.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.61.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.62.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.47.mlp.experts.63.up_proj.weight": "model-00048-of-00052.safetensors", - "model.layers.48.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.48.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.49.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.50.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.51.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.52.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.53.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.54.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.55.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.56.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.57.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.58.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.59.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.60.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.61.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.62.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.63.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.64.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.56.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.57.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.58.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.59.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.60.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.61.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.62.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.65.mlp.experts.63.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.0.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.1.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.2.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.3.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.4.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.5.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.6.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.7.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.8.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.9.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.10.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.11.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.12.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.13.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.14.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.15.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.16.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.17.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.18.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.19.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.20.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.21.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.22.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.23.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.24.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.25.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.26.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.27.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.28.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.29.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.30.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.31.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.32.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.33.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.34.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.35.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.36.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.37.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.38.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.39.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.40.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.41.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.42.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.43.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.44.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.45.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.46.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.47.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.48.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.49.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.50.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.51.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.52.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.53.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.54.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.55.up_proj.weight": "model-00049-of-00052.safetensors", - "model.layers.66.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.66.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.66.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.66.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.66.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.66.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.66.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.66.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.67.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.68.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.69.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.70.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.71.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.72.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.73.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.74.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.75.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.76.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.77.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.78.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.79.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.80.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.81.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.82.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.83.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.48.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.49.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.50.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.51.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.52.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.53.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.54.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.55.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.56.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.57.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.58.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.59.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.60.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.61.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.62.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.84.mlp.experts.63.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.0.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.1.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.2.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.3.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.4.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.5.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.6.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.7.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.8.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.9.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.10.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.11.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.12.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.13.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.14.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.15.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.16.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.17.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.18.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.19.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.20.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.21.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.22.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.23.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.24.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.25.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.26.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.27.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.28.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.29.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.30.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.31.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.32.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.33.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.34.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.35.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.36.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.37.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.38.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.39.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.40.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.41.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.42.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.43.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.44.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.45.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.46.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.47.up_proj.weight": "model-00050-of-00052.safetensors", - "model.layers.85.mlp.experts.48.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.49.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.50.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.51.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.52.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.53.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.54.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.55.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.56.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.57.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.58.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.59.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.60.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.61.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.62.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.experts.63.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.0.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.1.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.2.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.3.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.4.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.5.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.6.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.7.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.8.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.9.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.10.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.11.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.12.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.13.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.14.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.15.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.16.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.17.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.18.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.19.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.20.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.21.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.22.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.23.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.24.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.25.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.26.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.27.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.28.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.29.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.30.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.31.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.32.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.33.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.34.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.35.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.36.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.37.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.38.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.39.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.40.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.41.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.42.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.43.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.44.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.45.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.46.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.47.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.48.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.49.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.50.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.51.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.52.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.53.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.54.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.55.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.56.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.57.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.58.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.59.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.60.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.61.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.62.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.experts.63.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.0.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.1.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.2.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.3.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.4.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.5.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.6.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.7.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.8.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.9.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.10.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.11.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.12.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.13.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.14.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.15.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.16.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.17.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.18.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.19.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.20.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.21.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.22.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.23.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.24.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.25.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.26.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.27.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.28.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.29.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.30.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.31.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.32.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.33.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.34.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.35.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.36.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.37.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.38.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.39.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.40.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.41.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.42.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.43.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.44.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.45.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.46.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.47.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.48.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.49.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.50.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.51.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.52.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.53.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.54.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.55.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.56.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.57.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.58.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.59.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.60.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.61.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.62.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.experts.63.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.0.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.48.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.49.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.50.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.51.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.52.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.53.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.54.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.55.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.56.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.57.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.58.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.59.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.60.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.61.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.62.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.63.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.64.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.65.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.66.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.67.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.68.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.69.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.70.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.71.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.72.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.73.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.74.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.75.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.76.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.77.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.78.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.79.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.80.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.81.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.82.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.83.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.84.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.85.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.86.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.87.mlp.shared_experts.up_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.0.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00051-of-00052.safetensors", - "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.48.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.49.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.50.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.51.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.52.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.53.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.54.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.55.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.56.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.57.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.58.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.59.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.60.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.61.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.62.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.63.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.64.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.65.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.66.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.67.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.68.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.69.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.70.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.71.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.72.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.73.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.74.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.75.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.76.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.77.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.78.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.79.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.80.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.81.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.82.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.83.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.84.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.85.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.86.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors", - "model.layers.87.mlp.shared_experts.down_proj.weight": "model-00052-of-00052.safetensors" + "model.layers.0.attention.dense.weight": "model-00001-of-00045.safetensors", + "model.layers.0.attention.query_key_value.weight": "model-00001-of-00045.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.10.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.10.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.10.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.11.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.11.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.11.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.12.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.12.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.12.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.13.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.13.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.13.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.14.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.14.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.14.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.15.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.15.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.15.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.16.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.16.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.16.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.17.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.17.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.17.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.18.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.18.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.18.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.19.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.19.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.19.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.2.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.2.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.20.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.20.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.20.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.21.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.21.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.21.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.22.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.22.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.22.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.23.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.23.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.23.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.24.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.24.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.24.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.25.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.25.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.25.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.26.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.26.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.26.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.27.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.27.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.27.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.28.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.28.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.28.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.29.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.29.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.29.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.3.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.3.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.30.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.30.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.30.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.31.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.31.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.31.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.32.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.32.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.32.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.33.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.33.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.33.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.34.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.34.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.34.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.35.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.35.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.35.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.36.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.36.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.36.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.37.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.37.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.37.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.38.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.38.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.38.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.39.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.39.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.39.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.4.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.4.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.4.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.40.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.40.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.40.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.41.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.41.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.41.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.42.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.42.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.42.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.43.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.43.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.43.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.44.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.44.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.44.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.45.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.45.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.45.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.46.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.46.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.46.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.47.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.47.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.47.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.48.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.48.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.48.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.49.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.49.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.49.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.5.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.5.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.5.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.50.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.50.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.50.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.51.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.51.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.51.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.52.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.52.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.52.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.53.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.53.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.53.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.54.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.54.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.54.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.55.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.55.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.55.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.56.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.56.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.56.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.57.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.57.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.57.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.58.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.58.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.58.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.59.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.59.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.59.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.6.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.6.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.6.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.60.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.60.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.60.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.61.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.61.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.61.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.62.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.62.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.62.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.63.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.63.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.63.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.7.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.7.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.7.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.8.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.8.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.8.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.9.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.9.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.experts.9.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.gate.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.shared_experts.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.shared_experts.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.mlp.shared_experts.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00045.safetensors", + "model.layers.1.attention.dense.weight": "model-00001-of-00045.safetensors", + "model.layers.1.attention.query_key_value.weight": "model-00001-of-00045.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.gate.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00045.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00045.safetensors", + "model.layers.2.attention.dense.weight": "model-00002-of-00045.safetensors", + "model.layers.2.attention.query_key_value.weight": "model-00002-of-00045.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.gate.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00045.safetensors", + "model.layers.3.attention.dense.weight": "model-00002-of-00045.safetensors", + "model.layers.3.attention.query_key_value.weight": "model-00002-of-00045.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.gate.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00002-of-00045.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00045.safetensors", + "model.layers.4.attention.dense.weight": "model-00003-of-00045.safetensors", + "model.layers.4.attention.query_key_value.weight": "model-00003-of-00045.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.gate.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00045.safetensors", + "model.layers.5.attention.dense.weight": "model-00003-of-00045.safetensors", + "model.layers.5.attention.query_key_value.weight": "model-00003-of-00045.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.gate.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00003-of-00045.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00045.safetensors", + "model.layers.6.attention.dense.weight": "model-00004-of-00045.safetensors", + "model.layers.6.attention.query_key_value.weight": "model-00004-of-00045.safetensors", + "model.layers.6.input_layernorm.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.gate.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00045.safetensors", + "model.layers.7.attention.dense.weight": "model-00004-of-00045.safetensors", + "model.layers.7.attention.query_key_value.weight": "model-00004-of-00045.safetensors", + "model.layers.7.input_layernorm.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.gate.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00004-of-00045.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00045.safetensors", + "model.layers.8.attention.dense.weight": "model-00005-of-00045.safetensors", + "model.layers.8.attention.query_key_value.weight": "model-00005-of-00045.safetensors", + "model.layers.8.input_layernorm.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.gate.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00045.safetensors", + "model.layers.9.attention.dense.weight": "model-00005-of-00045.safetensors", + "model.layers.9.attention.query_key_value.weight": "model-00005-of-00045.safetensors", + "model.layers.9.input_layernorm.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.gate.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00005-of-00045.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00045.safetensors", + "model.layers.10.attention.dense.weight": "model-00006-of-00045.safetensors", + "model.layers.10.attention.query_key_value.weight": "model-00006-of-00045.safetensors", + "model.layers.10.input_layernorm.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.gate.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00045.safetensors", + "model.layers.11.attention.dense.weight": "model-00006-of-00045.safetensors", + "model.layers.11.attention.query_key_value.weight": "model-00006-of-00045.safetensors", + "model.layers.11.input_layernorm.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.gate.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00006-of-00045.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00045.safetensors", + "model.layers.12.attention.dense.weight": "model-00007-of-00045.safetensors", + "model.layers.12.attention.query_key_value.weight": "model-00007-of-00045.safetensors", + "model.layers.12.input_layernorm.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.gate.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00045.safetensors", + "model.layers.13.attention.dense.weight": "model-00007-of-00045.safetensors", + "model.layers.13.attention.query_key_value.weight": "model-00007-of-00045.safetensors", + "model.layers.13.input_layernorm.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.gate.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00007-of-00045.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00045.safetensors", + "model.layers.14.attention.dense.weight": "model-00008-of-00045.safetensors", + "model.layers.14.attention.query_key_value.weight": "model-00008-of-00045.safetensors", + "model.layers.14.input_layernorm.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.gate.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00045.safetensors", + "model.layers.15.attention.dense.weight": "model-00008-of-00045.safetensors", + "model.layers.15.attention.query_key_value.weight": "model-00008-of-00045.safetensors", + "model.layers.15.input_layernorm.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.gate.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00008-of-00045.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00045.safetensors", + "model.layers.16.attention.dense.weight": "model-00009-of-00045.safetensors", + "model.layers.16.attention.query_key_value.weight": "model-00009-of-00045.safetensors", + "model.layers.16.input_layernorm.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.gate.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00045.safetensors", + "model.layers.17.attention.dense.weight": "model-00009-of-00045.safetensors", + "model.layers.17.attention.query_key_value.weight": "model-00009-of-00045.safetensors", + "model.layers.17.input_layernorm.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.gate.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00009-of-00045.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00045.safetensors", + "model.layers.18.attention.dense.weight": "model-00010-of-00045.safetensors", + "model.layers.18.attention.query_key_value.weight": "model-00010-of-00045.safetensors", + "model.layers.18.input_layernorm.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.gate.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00045.safetensors", + "model.layers.19.attention.dense.weight": "model-00010-of-00045.safetensors", + "model.layers.19.attention.query_key_value.weight": "model-00010-of-00045.safetensors", + "model.layers.19.input_layernorm.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.gate.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00010-of-00045.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00045.safetensors", + "model.layers.20.attention.dense.weight": "model-00011-of-00045.safetensors", + "model.layers.20.attention.query_key_value.weight": "model-00011-of-00045.safetensors", + "model.layers.20.input_layernorm.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.gate.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00045.safetensors", + "model.layers.21.attention.dense.weight": "model-00011-of-00045.safetensors", + "model.layers.21.attention.query_key_value.weight": "model-00011-of-00045.safetensors", + "model.layers.21.input_layernorm.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.gate.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00011-of-00045.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00045.safetensors", + "model.layers.22.attention.dense.weight": "model-00012-of-00045.safetensors", + "model.layers.22.attention.query_key_value.weight": "model-00012-of-00045.safetensors", + "model.layers.22.input_layernorm.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.gate.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00045.safetensors", + "model.layers.23.attention.dense.weight": "model-00012-of-00045.safetensors", + "model.layers.23.attention.query_key_value.weight": "model-00012-of-00045.safetensors", + "model.layers.23.input_layernorm.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.gate.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00012-of-00045.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00045.safetensors", + "model.layers.24.attention.dense.weight": "model-00013-of-00045.safetensors", + "model.layers.24.attention.query_key_value.weight": "model-00013-of-00045.safetensors", + "model.layers.24.input_layernorm.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.gate.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00045.safetensors", + "model.layers.25.attention.dense.weight": "model-00013-of-00045.safetensors", + "model.layers.25.attention.query_key_value.weight": "model-00013-of-00045.safetensors", + "model.layers.25.input_layernorm.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.gate.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00013-of-00045.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00045.safetensors", + "model.layers.26.attention.dense.weight": "model-00014-of-00045.safetensors", + "model.layers.26.attention.query_key_value.weight": "model-00014-of-00045.safetensors", + "model.layers.26.input_layernorm.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.gate.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00045.safetensors", + "model.layers.27.attention.dense.weight": "model-00014-of-00045.safetensors", + "model.layers.27.attention.query_key_value.weight": "model-00014-of-00045.safetensors", + "model.layers.27.input_layernorm.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.gate.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00014-of-00045.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00045.safetensors", + "model.layers.28.attention.dense.weight": "model-00015-of-00045.safetensors", + "model.layers.28.attention.query_key_value.weight": "model-00015-of-00045.safetensors", + "model.layers.28.input_layernorm.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.gate.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00045.safetensors", + "model.layers.29.attention.dense.weight": "model-00015-of-00045.safetensors", + "model.layers.29.attention.query_key_value.weight": "model-00015-of-00045.safetensors", + "model.layers.29.input_layernorm.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.gate.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00015-of-00045.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00045.safetensors", + "model.layers.30.attention.dense.weight": "model-00016-of-00045.safetensors", + "model.layers.30.attention.query_key_value.weight": "model-00016-of-00045.safetensors", + "model.layers.30.input_layernorm.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.gate.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00016-of-00045.safetensors", + "model.layers.31.attention.dense.weight": "model-00016-of-00045.safetensors", + "model.layers.31.attention.query_key_value.weight": "model-00016-of-00045.safetensors", + "model.layers.31.input_layernorm.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.gate.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00016-of-00045.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00045.safetensors", + "model.layers.32.attention.dense.weight": "model-00017-of-00045.safetensors", + "model.layers.32.attention.query_key_value.weight": "model-00017-of-00045.safetensors", + "model.layers.32.input_layernorm.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.gate.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00017-of-00045.safetensors", + "model.layers.33.attention.dense.weight": "model-00017-of-00045.safetensors", + "model.layers.33.attention.query_key_value.weight": "model-00017-of-00045.safetensors", + "model.layers.33.input_layernorm.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.gate.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00017-of-00045.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00017-of-00045.safetensors", + "model.layers.34.attention.dense.weight": "model-00018-of-00045.safetensors", + "model.layers.34.attention.query_key_value.weight": "model-00018-of-00045.safetensors", + "model.layers.34.input_layernorm.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.gate.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00045.safetensors", + "model.layers.35.attention.dense.weight": "model-00018-of-00045.safetensors", + "model.layers.35.attention.query_key_value.weight": "model-00018-of-00045.safetensors", + "model.layers.35.input_layernorm.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.gate.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00018-of-00045.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00045.safetensors", + "model.layers.36.attention.dense.weight": "model-00019-of-00045.safetensors", + "model.layers.36.attention.query_key_value.weight": "model-00019-of-00045.safetensors", + "model.layers.36.input_layernorm.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.gate.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00019-of-00045.safetensors", + "model.layers.37.attention.dense.weight": "model-00019-of-00045.safetensors", + "model.layers.37.attention.query_key_value.weight": "model-00019-of-00045.safetensors", + "model.layers.37.input_layernorm.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.gate.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00019-of-00045.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00019-of-00045.safetensors", + "model.layers.38.attention.dense.weight": "model-00020-of-00045.safetensors", + "model.layers.38.attention.query_key_value.weight": "model-00020-of-00045.safetensors", + "model.layers.38.input_layernorm.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.gate.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00045.safetensors", + "model.layers.39.attention.dense.weight": "model-00020-of-00045.safetensors", + "model.layers.39.attention.query_key_value.weight": "model-00020-of-00045.safetensors", + "model.layers.39.input_layernorm.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.gate.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00020-of-00045.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00045.safetensors", + "model.layers.40.attention.dense.weight": "model-00021-of-00045.safetensors", + "model.layers.40.attention.query_key_value.weight": "model-00021-of-00045.safetensors", + "model.layers.40.input_layernorm.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.gate.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00045.safetensors", + "model.layers.41.attention.dense.weight": "model-00021-of-00045.safetensors", + "model.layers.41.attention.query_key_value.weight": "model-00021-of-00045.safetensors", + "model.layers.41.input_layernorm.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.gate.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00021-of-00045.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00021-of-00045.safetensors", + "model.layers.42.attention.dense.weight": "model-00022-of-00045.safetensors", + "model.layers.42.attention.query_key_value.weight": "model-00022-of-00045.safetensors", + "model.layers.42.input_layernorm.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.gate.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00022-of-00045.safetensors", + "model.layers.43.attention.dense.weight": "model-00022-of-00045.safetensors", + "model.layers.43.attention.query_key_value.weight": "model-00022-of-00045.safetensors", + "model.layers.43.input_layernorm.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.gate.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00022-of-00045.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00022-of-00045.safetensors", + "model.layers.44.attention.dense.weight": "model-00023-of-00045.safetensors", + "model.layers.44.attention.query_key_value.weight": "model-00023-of-00045.safetensors", + "model.layers.44.input_layernorm.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.gate.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00023-of-00045.safetensors", + "model.layers.45.attention.dense.weight": "model-00023-of-00045.safetensors", + "model.layers.45.attention.query_key_value.weight": "model-00023-of-00045.safetensors", + "model.layers.45.input_layernorm.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.gate.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00023-of-00045.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00023-of-00045.safetensors", + "model.layers.46.attention.dense.weight": "model-00024-of-00045.safetensors", + "model.layers.46.attention.query_key_value.weight": "model-00024-of-00045.safetensors", + "model.layers.46.input_layernorm.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.0.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.0.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.1.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.1.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.10.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.10.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.11.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.11.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.12.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.12.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.13.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.13.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.14.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.14.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.15.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.15.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.16.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.16.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.17.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.17.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.18.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.18.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.19.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.19.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.2.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.2.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.20.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.20.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.21.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.21.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.22.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.22.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.23.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.23.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.24.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.24.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.25.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.25.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.26.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.26.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.27.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.27.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.28.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.28.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.29.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.29.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.3.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.3.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.30.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.30.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.31.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.31.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.32.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.32.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.33.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.33.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.34.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.34.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.35.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.35.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.36.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.36.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.37.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.37.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.38.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.38.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.39.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.39.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.4.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.4.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.40.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.40.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.41.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.41.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.42.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.42.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.43.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.43.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.44.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.44.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.45.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.45.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.46.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.46.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.47.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.47.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.48.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.48.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.49.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.49.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.5.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.5.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.50.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.50.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.51.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.51.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.52.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.52.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.53.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.53.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.54.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.54.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.55.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.55.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.56.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.56.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.57.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.57.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.58.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.58.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.59.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.59.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.6.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.6.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.60.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.60.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.61.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.61.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.62.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.62.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.63.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.63.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.7.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.7.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.8.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.8.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.9.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.experts.9.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.gate.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00024-of-00045.safetensors", + "model.layers.47.attention.dense.weight": "model-00024-of-00045.safetensors", + "model.layers.47.attention.query_key_value.weight": "model-00024-of-00045.safetensors", + "model.layers.47.input_layernorm.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.0.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.0.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.0.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.1.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.1.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.1.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.10.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.10.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.10.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.11.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.11.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.11.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.12.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.12.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.12.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.13.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.13.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.13.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.14.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.14.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.14.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.15.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.15.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.15.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.16.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.16.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.16.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.17.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.17.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.17.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.18.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.18.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.18.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.19.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.19.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.19.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.2.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.2.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.2.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.20.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.20.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.20.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.21.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.21.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.21.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.22.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.22.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.22.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.23.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.23.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.23.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.24.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.24.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.24.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.25.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.25.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.25.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.26.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.26.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.26.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.27.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.27.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.27.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.28.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.28.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.28.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.29.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.29.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.29.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.3.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.3.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.3.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.30.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.30.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.30.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.31.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.31.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.31.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.32.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.32.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.32.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.33.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.33.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.33.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.34.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.34.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.34.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.35.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.35.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.35.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.36.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.36.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.36.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.37.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.37.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.37.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.38.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.38.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.38.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.39.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.39.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.39.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.4.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.4.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.4.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.40.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.40.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.40.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.41.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.41.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.41.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.42.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.42.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.42.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.43.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.43.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.43.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.44.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.44.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.44.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.45.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.45.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.45.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.46.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.46.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.46.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.47.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.47.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.47.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.48.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.48.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.48.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.49.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.49.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.49.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.5.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.5.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.5.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.50.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.50.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.50.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.51.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.51.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.51.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.52.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.52.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.52.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.53.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.53.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.53.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.54.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.54.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.54.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.55.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.55.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.55.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.56.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.56.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.56.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.57.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.57.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.57.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.58.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.58.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.58.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.59.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.59.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.59.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.6.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.6.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.6.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.60.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.60.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.60.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.61.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.61.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.61.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.62.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.62.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.62.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.63.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.63.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.63.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.7.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.7.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.7.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.8.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.8.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.8.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.9.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.9.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.experts.9.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.gate.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00024-of-00045.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00024-of-00045.safetensors", + "model.layers.48.attention.dense.weight": "model-00025-of-00045.safetensors", + "model.layers.48.attention.query_key_value.weight": "model-00025-of-00045.safetensors", + "model.layers.48.input_layernorm.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.0.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.0.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.0.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.1.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.1.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.1.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.10.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.10.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.10.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.11.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.11.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.11.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.12.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.12.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.12.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.13.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.13.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.13.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.14.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.14.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.14.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.15.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.15.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.15.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.16.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.16.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.16.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.17.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.17.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.17.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.18.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.18.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.18.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.19.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.19.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.19.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.2.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.2.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.2.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.20.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.20.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.20.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.21.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.21.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.21.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.22.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.22.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.22.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.23.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.23.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.23.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.24.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.24.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.24.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.25.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.25.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.25.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.26.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.26.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.26.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.27.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.27.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.27.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.28.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.28.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.28.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.29.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.29.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.29.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.3.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.3.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.3.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.30.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.30.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.30.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.31.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.31.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.31.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.32.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.32.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.32.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.33.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.33.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.33.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.34.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.34.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.34.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.35.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.35.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.35.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.36.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.36.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.36.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.37.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.37.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.37.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.38.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.38.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.38.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.39.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.39.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.39.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.4.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.4.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.4.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.40.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.40.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.40.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.41.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.41.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.41.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.42.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.42.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.42.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.43.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.43.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.43.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.44.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.44.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.44.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.45.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.45.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.45.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.46.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.46.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.46.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.47.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.47.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.47.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.48.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.48.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.48.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.49.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.49.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.49.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.5.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.5.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.5.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.50.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.50.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.50.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.51.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.51.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.51.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.52.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.52.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.52.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.53.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.53.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.53.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.54.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.54.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.54.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.55.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.55.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.55.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.56.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.56.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.56.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.57.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.57.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.57.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.58.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.58.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.58.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.59.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.59.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.59.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.6.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.6.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.6.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.60.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.60.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.60.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.61.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.61.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.61.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.62.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.62.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.62.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.63.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.63.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.63.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.7.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.7.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.7.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.8.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.8.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.8.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.9.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.9.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.experts.9.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.gate.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00025-of-00045.safetensors", + "model.layers.49.attention.dense.weight": "model-00025-of-00045.safetensors", + "model.layers.49.attention.query_key_value.weight": "model-00025-of-00045.safetensors", + "model.layers.49.input_layernorm.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.0.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.0.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.0.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.1.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.1.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.1.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.10.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.10.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.10.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.11.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.11.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.11.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.12.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.12.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.12.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.13.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.13.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.13.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.14.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.14.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.14.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.15.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.15.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.15.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.16.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.16.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.16.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.17.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.17.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.17.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.18.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.18.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.18.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.19.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.19.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.19.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.2.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.2.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.2.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.20.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.20.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.20.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.21.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.21.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.21.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.22.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.22.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.22.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.23.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.23.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.23.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.24.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.24.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.24.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.25.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.25.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.25.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.26.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.26.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.26.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.27.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.27.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.27.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.28.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.28.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.28.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.29.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.29.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.29.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.3.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.3.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.3.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.30.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.30.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.30.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.31.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.31.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.31.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.32.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.32.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.32.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.33.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.33.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.33.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.34.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.34.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.34.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.35.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.35.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.35.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.36.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.36.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.36.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.37.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.37.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.37.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.38.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.38.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.38.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.39.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.39.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.39.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.4.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.4.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.4.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.40.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.40.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.40.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.41.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.41.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.41.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.42.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.42.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.42.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.43.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.43.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.43.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.44.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.44.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.44.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.45.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.45.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.45.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.46.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.46.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.46.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.47.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.47.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.47.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.48.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.48.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.48.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.49.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.49.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.49.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.5.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.5.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.5.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.50.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.50.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.50.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.51.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.51.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.51.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.52.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.52.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.52.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.53.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.53.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.53.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.54.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.54.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.54.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.55.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.55.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.55.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.56.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.56.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.56.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.57.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.57.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.57.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.58.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.58.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.58.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.59.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.59.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.59.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.6.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.6.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.6.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.60.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.60.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.60.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.61.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.61.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.61.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.62.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.62.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.62.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.63.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.63.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.63.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.7.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.7.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.7.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.8.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.8.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.8.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.9.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.9.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.experts.9.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.gate.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.weight": "model-00025-of-00045.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00025-of-00045.safetensors", + "model.layers.50.attention.dense.weight": "model-00026-of-00045.safetensors", + "model.layers.50.attention.query_key_value.weight": "model-00026-of-00045.safetensors", + "model.layers.50.input_layernorm.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.0.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.0.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.0.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.1.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.1.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.1.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.10.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.10.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.10.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.11.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.11.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.11.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.12.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.12.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.12.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.13.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.13.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.13.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.14.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.14.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.14.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.15.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.15.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.15.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.16.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.16.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.16.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.17.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.17.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.17.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.18.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.18.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.18.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.19.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.19.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.19.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.2.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.2.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.2.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.20.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.20.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.20.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.21.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.21.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.21.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.22.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.22.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.22.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.23.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.23.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.23.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.24.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.24.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.24.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.25.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.25.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.25.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.26.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.26.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.26.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.27.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.27.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.27.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.28.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.28.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.28.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.29.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.29.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.29.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.3.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.3.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.3.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.30.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.30.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.30.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.31.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.31.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.31.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.32.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.32.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.32.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.33.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.33.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.33.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.34.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.34.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.34.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.35.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.35.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.35.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.36.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.36.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.36.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.37.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.37.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.37.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.38.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.38.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.38.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.39.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.39.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.39.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.4.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.4.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.4.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.40.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.40.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.40.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.41.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.41.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.41.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.42.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.42.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.42.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.43.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.43.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.43.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.44.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.44.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.44.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.45.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.45.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.45.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.46.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.46.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.46.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.47.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.47.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.47.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.48.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.48.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.48.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.49.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.49.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.49.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.5.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.5.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.5.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.50.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.50.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.50.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.51.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.51.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.51.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.52.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.52.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.52.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.53.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.53.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.53.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.54.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.54.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.54.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.55.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.55.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.55.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.56.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.56.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.56.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.57.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.57.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.57.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.58.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.58.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.58.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.59.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.59.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.59.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.6.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.6.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.6.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.60.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.60.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.60.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.61.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.61.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.61.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.62.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.62.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.62.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.63.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.63.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.63.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.7.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.7.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.7.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.8.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.8.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.8.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.9.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.9.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.experts.9.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.gate.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00026-of-00045.safetensors", + "model.layers.51.attention.dense.weight": "model-00026-of-00045.safetensors", + "model.layers.51.attention.query_key_value.weight": "model-00026-of-00045.safetensors", + "model.layers.51.input_layernorm.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.0.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.0.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.0.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.1.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.1.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.1.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.10.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.10.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.10.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.11.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.11.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.11.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.12.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.12.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.12.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.13.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.13.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.13.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.14.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.14.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.14.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.15.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.15.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.15.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.16.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.16.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.16.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.17.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.17.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.17.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.18.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.18.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.18.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.19.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.19.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.19.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.2.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.2.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.2.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.20.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.20.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.20.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.21.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.21.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.21.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.22.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.22.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.22.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.23.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.23.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.23.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.24.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.24.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.24.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.25.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.25.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.25.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.26.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.26.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.26.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.27.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.27.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.27.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.28.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.28.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.28.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.29.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.29.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.29.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.3.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.3.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.3.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.30.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.30.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.30.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.31.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.31.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.31.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.32.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.32.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.32.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.33.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.33.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.33.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.34.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.34.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.34.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.35.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.35.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.35.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.36.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.36.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.36.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.37.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.37.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.37.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.38.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.38.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.38.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.39.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.39.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.39.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.4.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.4.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.4.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.40.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.40.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.40.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.41.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.41.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.41.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.42.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.42.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.42.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.43.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.43.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.43.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.44.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.44.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.44.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.45.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.45.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.45.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.46.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.46.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.46.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.47.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.47.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.47.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.48.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.48.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.48.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.49.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.49.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.49.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.5.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.5.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.5.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.50.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.50.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.50.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.51.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.51.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.51.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.52.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.52.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.52.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.53.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.53.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.53.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.54.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.54.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.54.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.55.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.55.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.55.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.56.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.56.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.56.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.57.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.57.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.57.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.58.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.58.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.58.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.59.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.59.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.59.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.6.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.6.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.6.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.60.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.60.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.60.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.61.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.61.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.61.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.62.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.62.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.62.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.63.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.63.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.63.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.7.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.7.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.7.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.8.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.8.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.8.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.9.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.9.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.experts.9.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.gate.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.weight": "model-00026-of-00045.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00026-of-00045.safetensors", + "model.layers.52.attention.dense.weight": "model-00027-of-00045.safetensors", + "model.layers.52.attention.query_key_value.weight": "model-00027-of-00045.safetensors", + "model.layers.52.input_layernorm.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.0.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.0.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.0.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.1.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.1.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.1.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.10.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.10.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.10.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.11.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.11.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.11.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.12.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.12.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.12.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.13.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.13.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.13.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.14.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.14.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.14.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.15.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.15.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.15.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.16.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.16.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.16.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.17.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.17.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.17.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.18.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.18.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.18.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.19.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.19.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.19.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.2.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.2.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.2.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.20.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.20.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.20.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.21.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.21.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.21.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.22.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.22.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.22.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.23.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.23.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.23.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.24.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.24.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.24.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.25.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.25.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.25.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.26.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.26.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.26.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.27.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.27.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.27.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.28.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.28.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.28.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.29.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.29.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.29.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.3.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.3.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.3.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.30.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.30.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.30.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.31.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.31.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.31.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.32.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.32.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.32.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.33.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.33.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.33.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.34.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.34.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.34.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.35.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.35.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.35.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.36.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.36.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.36.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.37.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.37.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.37.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.38.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.38.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.38.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.39.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.39.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.39.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.4.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.4.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.4.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.40.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.40.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.40.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.41.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.41.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.41.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.42.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.42.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.42.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.43.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.43.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.43.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.44.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.44.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.44.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.45.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.45.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.45.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.46.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.46.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.46.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.47.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.47.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.47.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.48.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.48.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.48.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.49.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.49.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.49.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.5.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.5.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.5.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.50.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.50.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.50.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.51.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.51.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.51.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.52.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.52.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.52.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.53.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.53.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.53.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.54.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.54.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.54.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.55.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.55.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.55.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.56.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.56.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.56.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.57.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.57.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.57.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.58.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.58.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.58.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.59.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.59.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.59.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.6.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.6.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.6.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.60.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.60.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.60.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.61.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.61.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.61.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.62.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.62.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.62.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.63.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.63.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.63.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.7.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.7.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.7.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.8.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.8.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.8.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.9.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.9.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.experts.9.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.gate.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00027-of-00045.safetensors", + "model.layers.53.attention.dense.weight": "model-00027-of-00045.safetensors", + "model.layers.53.attention.query_key_value.weight": "model-00027-of-00045.safetensors", + "model.layers.53.input_layernorm.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.0.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.0.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.0.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.1.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.1.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.1.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.10.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.10.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.10.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.11.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.11.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.11.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.12.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.12.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.12.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.13.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.13.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.13.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.14.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.14.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.14.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.15.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.15.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.15.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.16.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.16.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.16.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.17.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.17.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.17.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.18.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.18.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.18.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.19.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.19.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.19.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.2.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.2.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.2.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.20.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.20.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.20.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.21.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.21.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.21.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.22.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.22.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.22.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.23.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.23.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.23.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.24.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.24.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.24.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.25.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.25.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.25.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.26.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.26.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.26.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.27.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.27.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.27.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.28.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.28.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.28.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.29.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.29.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.29.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.3.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.3.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.3.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.30.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.30.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.30.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.31.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.31.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.31.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.32.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.32.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.32.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.33.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.33.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.33.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.34.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.34.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.34.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.35.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.35.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.35.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.36.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.36.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.36.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.37.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.37.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.37.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.38.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.38.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.38.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.39.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.39.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.39.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.4.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.4.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.4.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.40.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.40.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.40.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.41.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.41.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.41.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.42.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.42.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.42.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.43.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.43.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.43.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.44.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.44.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.44.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.45.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.45.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.45.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.46.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.46.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.46.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.47.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.47.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.47.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.48.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.48.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.48.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.49.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.49.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.49.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.5.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.5.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.5.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.50.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.50.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.50.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.51.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.51.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.51.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.52.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.52.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.52.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.53.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.53.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.53.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.54.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.54.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.54.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.55.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.55.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.55.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.56.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.56.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.56.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.57.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.57.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.57.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.58.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.58.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.58.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.59.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.59.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.59.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.6.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.6.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.6.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.60.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.60.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.60.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.61.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.61.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.61.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.62.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.62.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.62.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.63.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.63.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.63.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.7.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.7.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.7.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.8.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.8.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.8.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.9.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.9.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.experts.9.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.gate.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.weight": "model-00027-of-00045.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00027-of-00045.safetensors", + "model.layers.54.attention.dense.weight": "model-00028-of-00045.safetensors", + "model.layers.54.attention.query_key_value.weight": "model-00028-of-00045.safetensors", + "model.layers.54.input_layernorm.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.0.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.0.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.0.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.1.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.1.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.1.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.10.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.10.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.10.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.11.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.11.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.11.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.12.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.12.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.12.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.13.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.13.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.13.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.14.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.14.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.14.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.15.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.15.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.15.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.16.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.16.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.16.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.17.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.17.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.17.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.18.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.18.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.18.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.19.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.19.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.19.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.2.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.2.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.2.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.20.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.20.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.20.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.21.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.21.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.21.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.22.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.22.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.22.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.23.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.23.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.23.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.24.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.24.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.24.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.25.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.25.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.25.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.26.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.26.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.26.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.27.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.27.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.27.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.28.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.28.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.28.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.29.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.29.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.29.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.3.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.3.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.3.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.30.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.30.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.30.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.31.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.31.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.31.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.32.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.32.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.32.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.33.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.33.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.33.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.34.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.34.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.34.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.35.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.35.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.35.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.36.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.36.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.36.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.37.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.37.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.37.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.38.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.38.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.38.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.39.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.39.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.39.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.4.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.4.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.4.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.40.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.40.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.40.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.41.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.41.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.41.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.42.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.42.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.42.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.43.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.43.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.43.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.44.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.44.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.44.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.45.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.45.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.45.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.46.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.46.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.46.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.47.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.47.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.47.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.48.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.48.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.48.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.49.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.49.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.49.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.5.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.5.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.5.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.50.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.50.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.50.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.51.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.51.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.51.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.52.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.52.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.52.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.53.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.53.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.53.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.54.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.54.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.54.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.55.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.55.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.55.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.56.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.56.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.56.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.57.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.57.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.57.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.58.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.58.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.58.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.59.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.59.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.59.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.6.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.6.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.6.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.60.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.60.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.60.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.61.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.61.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.61.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.62.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.62.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.62.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.63.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.63.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.63.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.7.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.7.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.7.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.8.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.8.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.8.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.9.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.9.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.experts.9.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.gate.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00028-of-00045.safetensors", + "model.layers.55.attention.dense.weight": "model-00028-of-00045.safetensors", + "model.layers.55.attention.query_key_value.weight": "model-00028-of-00045.safetensors", + "model.layers.55.input_layernorm.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.0.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.0.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.0.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.1.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.1.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.1.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.10.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.10.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.10.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.11.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.11.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.11.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.12.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.12.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.12.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.13.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.13.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.13.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.14.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.14.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.14.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.15.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.15.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.15.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.16.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.16.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.16.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.17.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.17.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.17.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.18.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.18.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.18.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.19.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.19.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.19.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.2.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.2.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.2.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.20.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.20.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.20.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.21.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.21.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.21.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.22.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.22.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.22.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.23.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.23.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.23.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.24.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.24.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.24.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.25.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.25.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.25.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.26.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.26.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.26.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.27.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.27.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.27.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.28.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.28.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.28.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.29.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.29.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.29.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.3.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.3.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.3.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.30.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.30.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.30.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.31.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.31.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.31.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.32.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.32.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.32.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.33.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.33.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.33.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.34.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.34.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.34.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.35.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.35.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.35.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.36.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.36.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.36.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.37.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.37.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.37.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.38.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.38.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.38.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.39.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.39.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.39.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.4.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.4.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.4.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.40.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.40.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.40.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.41.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.41.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.41.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.42.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.42.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.42.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.43.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.43.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.43.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.44.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.44.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.44.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.45.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.45.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.45.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.46.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.46.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.46.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.47.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.47.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.47.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.48.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.48.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.48.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.49.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.49.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.49.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.5.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.5.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.5.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.50.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.50.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.50.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.51.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.51.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.51.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.52.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.52.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.52.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.53.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.53.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.53.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.54.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.54.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.54.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.55.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.55.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.55.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.56.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.56.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.56.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.57.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.57.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.57.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.58.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.58.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.58.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.59.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.59.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.59.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.6.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.6.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.6.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.60.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.60.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.60.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.61.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.61.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.61.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.62.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.62.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.62.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.63.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.63.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.63.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.7.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.7.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.7.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.8.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.8.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.8.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.9.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.9.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.experts.9.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.gate.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.weight": "model-00028-of-00045.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00028-of-00045.safetensors", + "model.layers.56.attention.dense.weight": "model-00029-of-00045.safetensors", + "model.layers.56.attention.query_key_value.weight": "model-00029-of-00045.safetensors", + "model.layers.56.input_layernorm.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.0.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.0.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.0.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.1.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.1.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.1.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.10.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.10.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.10.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.11.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.11.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.11.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.12.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.12.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.12.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.13.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.13.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.13.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.14.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.14.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.14.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.15.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.15.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.15.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.16.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.16.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.16.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.17.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.17.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.17.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.18.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.18.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.18.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.19.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.19.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.19.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.2.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.2.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.2.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.20.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.20.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.20.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.21.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.21.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.21.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.22.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.22.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.22.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.23.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.23.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.23.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.24.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.24.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.24.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.25.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.25.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.25.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.26.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.26.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.26.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.27.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.27.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.27.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.28.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.28.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.28.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.29.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.29.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.29.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.3.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.3.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.3.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.30.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.30.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.30.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.31.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.31.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.31.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.32.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.32.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.32.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.33.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.33.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.33.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.34.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.34.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.34.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.35.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.35.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.35.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.36.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.36.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.36.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.37.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.37.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.37.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.38.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.38.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.38.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.39.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.39.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.39.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.4.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.4.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.4.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.40.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.40.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.40.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.41.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.41.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.41.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.42.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.42.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.42.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.43.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.43.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.43.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.44.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.44.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.44.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.45.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.45.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.45.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.46.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.46.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.46.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.47.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.47.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.47.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.48.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.48.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.48.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.49.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.49.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.49.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.5.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.5.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.5.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.50.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.50.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.50.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.51.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.51.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.51.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.52.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.52.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.52.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.53.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.53.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.53.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.54.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.54.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.54.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.55.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.55.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.55.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.56.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.56.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.56.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.57.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.57.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.57.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.58.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.58.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.58.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.59.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.59.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.59.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.6.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.6.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.6.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.60.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.60.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.60.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.61.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.61.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.61.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.62.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.62.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.62.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.63.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.63.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.63.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.7.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.7.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.7.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.8.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.8.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.8.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.9.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.9.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.experts.9.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.gate.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00029-of-00045.safetensors", + "model.layers.57.attention.dense.weight": "model-00029-of-00045.safetensors", + "model.layers.57.attention.query_key_value.weight": "model-00029-of-00045.safetensors", + "model.layers.57.input_layernorm.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.0.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.0.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.0.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.1.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.1.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.1.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.10.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.10.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.10.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.11.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.11.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.11.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.12.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.12.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.12.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.13.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.13.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.13.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.14.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.14.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.14.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.15.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.15.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.15.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.16.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.16.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.16.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.17.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.17.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.17.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.18.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.18.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.18.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.19.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.19.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.19.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.2.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.2.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.2.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.20.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.20.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.20.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.21.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.21.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.21.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.22.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.22.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.22.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.23.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.23.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.23.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.24.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.24.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.24.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.25.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.25.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.25.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.26.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.26.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.26.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.27.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.27.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.27.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.28.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.28.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.28.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.29.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.29.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.29.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.3.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.3.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.3.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.30.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.30.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.30.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.31.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.31.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.31.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.32.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.32.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.32.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.33.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.33.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.33.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.34.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.34.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.34.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.35.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.35.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.35.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.36.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.36.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.36.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.37.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.37.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.37.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.38.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.38.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.38.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.39.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.39.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.39.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.4.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.4.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.4.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.40.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.40.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.40.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.41.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.41.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.41.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.42.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.42.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.42.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.43.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.43.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.43.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.44.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.44.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.44.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.45.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.45.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.45.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.46.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.46.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.46.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.47.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.47.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.47.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.48.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.48.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.48.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.49.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.49.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.49.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.5.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.5.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.5.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.50.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.50.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.50.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.51.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.51.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.51.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.52.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.52.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.52.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.53.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.53.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.53.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.54.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.54.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.54.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.55.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.55.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.55.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.56.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.56.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.56.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.57.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.57.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.57.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.58.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.58.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.58.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.59.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.59.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.59.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.6.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.6.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.6.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.60.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.60.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.60.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.61.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.61.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.61.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.62.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.62.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.62.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.63.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.63.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.63.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.7.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.7.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.7.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.8.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.8.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.8.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.9.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.9.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.experts.9.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.gate.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.weight": "model-00029-of-00045.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00029-of-00045.safetensors", + "model.layers.58.attention.dense.weight": "model-00030-of-00045.safetensors", + "model.layers.58.attention.query_key_value.weight": "model-00030-of-00045.safetensors", + "model.layers.58.input_layernorm.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.0.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.0.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.0.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.1.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.1.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.1.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.10.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.10.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.10.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.11.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.11.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.11.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.12.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.12.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.12.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.13.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.13.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.13.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.14.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.14.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.14.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.15.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.15.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.15.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.16.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.16.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.16.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.17.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.17.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.17.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.18.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.18.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.18.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.19.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.19.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.19.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.2.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.2.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.2.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.20.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.20.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.20.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.21.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.21.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.21.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.22.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.22.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.22.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.23.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.23.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.23.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.24.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.24.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.24.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.25.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.25.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.25.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.26.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.26.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.26.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.27.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.27.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.27.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.28.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.28.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.28.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.29.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.29.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.29.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.3.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.3.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.3.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.30.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.30.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.30.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.31.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.31.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.31.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.32.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.32.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.32.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.33.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.33.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.33.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.34.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.34.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.34.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.35.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.35.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.35.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.36.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.36.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.36.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.37.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.37.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.37.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.38.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.38.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.38.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.39.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.39.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.39.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.4.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.4.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.4.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.40.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.40.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.40.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.41.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.41.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.41.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.42.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.42.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.42.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.43.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.43.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.43.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.44.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.44.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.44.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.45.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.45.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.45.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.46.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.46.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.46.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.47.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.47.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.47.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.48.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.48.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.48.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.49.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.49.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.49.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.5.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.5.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.5.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.50.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.50.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.50.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.51.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.51.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.51.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.52.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.52.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.52.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.53.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.53.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.53.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.54.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.54.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.54.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.55.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.55.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.55.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.56.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.56.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.56.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.57.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.57.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.57.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.58.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.58.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.58.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.59.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.59.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.59.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.6.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.6.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.6.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.60.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.60.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.60.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.61.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.61.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.61.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.62.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.62.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.62.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.63.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.63.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.63.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.7.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.7.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.7.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.8.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.8.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.8.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.9.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.9.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.experts.9.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.gate.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00030-of-00045.safetensors", + "model.layers.59.attention.dense.weight": "model-00030-of-00045.safetensors", + "model.layers.59.attention.query_key_value.weight": "model-00030-of-00045.safetensors", + "model.layers.59.input_layernorm.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.0.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.0.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.0.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.1.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.1.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.1.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.10.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.10.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.10.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.11.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.11.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.11.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.12.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.12.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.12.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.13.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.13.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.13.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.14.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.14.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.14.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.15.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.15.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.15.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.16.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.16.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.16.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.17.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.17.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.17.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.18.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.18.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.18.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.19.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.19.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.19.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.2.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.2.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.2.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.20.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.20.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.20.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.21.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.21.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.21.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.22.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.22.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.22.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.23.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.23.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.23.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.24.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.24.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.24.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.25.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.25.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.25.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.26.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.26.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.26.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.27.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.27.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.27.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.28.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.28.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.28.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.29.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.29.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.29.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.3.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.3.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.3.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.30.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.30.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.30.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.31.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.31.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.31.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.32.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.32.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.32.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.33.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.33.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.33.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.34.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.34.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.34.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.35.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.35.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.35.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.36.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.36.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.36.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.37.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.37.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.37.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.38.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.38.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.38.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.39.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.39.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.39.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.4.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.4.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.4.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.40.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.40.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.40.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.41.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.41.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.41.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.42.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.42.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.42.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.43.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.43.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.43.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.44.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.44.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.44.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.45.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.45.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.45.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.46.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.46.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.46.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.47.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.47.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.47.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.48.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.48.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.48.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.49.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.49.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.49.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.5.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.5.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.5.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.50.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.50.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.50.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.51.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.51.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.51.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.52.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.52.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.52.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.53.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.53.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.53.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.54.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.54.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.54.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.55.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.55.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.55.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.56.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.56.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.56.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.57.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.57.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.57.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.58.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.58.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.58.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.59.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.59.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.59.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.6.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.6.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.6.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.60.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.60.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.60.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.61.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.61.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.61.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.62.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.62.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.62.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.63.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.63.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.63.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.7.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.7.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.7.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.8.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.8.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.8.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.9.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.9.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.experts.9.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.gate.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.weight": "model-00030-of-00045.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00030-of-00045.safetensors", + "model.layers.60.attention.dense.weight": "model-00031-of-00045.safetensors", + "model.layers.60.attention.query_key_value.weight": "model-00031-of-00045.safetensors", + "model.layers.60.input_layernorm.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.0.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.0.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.0.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.1.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.1.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.1.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.10.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.10.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.10.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.11.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.11.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.11.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.12.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.12.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.12.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.13.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.13.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.13.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.14.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.14.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.14.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.15.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.15.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.15.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.16.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.16.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.16.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.17.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.17.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.17.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.18.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.18.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.18.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.19.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.19.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.19.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.2.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.2.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.2.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.20.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.20.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.20.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.21.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.21.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.21.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.22.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.22.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.22.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.23.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.23.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.23.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.24.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.24.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.24.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.25.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.25.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.25.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.26.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.26.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.26.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.27.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.27.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.27.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.28.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.28.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.28.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.29.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.29.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.29.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.3.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.3.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.3.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.30.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.30.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.30.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.31.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.31.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.31.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.32.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.32.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.32.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.33.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.33.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.33.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.34.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.34.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.34.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.35.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.35.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.35.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.36.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.36.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.36.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.37.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.37.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.37.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.38.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.38.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.38.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.39.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.39.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.39.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.4.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.4.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.4.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.40.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.40.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.40.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.41.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.41.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.41.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.42.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.42.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.42.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.43.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.43.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.43.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.44.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.44.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.44.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.45.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.45.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.45.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.46.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.46.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.46.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.47.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.47.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.47.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.48.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.48.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.48.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.49.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.49.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.49.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.5.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.5.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.5.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.50.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.50.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.50.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.51.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.51.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.51.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.52.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.52.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.52.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.53.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.53.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.53.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.54.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.54.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.54.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.55.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.55.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.55.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.56.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.56.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.56.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.57.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.57.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.57.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.58.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.58.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.58.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.59.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.59.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.59.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.6.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.6.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.6.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.60.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.60.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.60.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.61.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.61.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.61.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.62.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.62.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.62.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.63.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.63.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.63.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.7.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.7.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.7.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.8.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.8.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.8.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.9.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.9.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.experts.9.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.gate.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00031-of-00045.safetensors", + "model.layers.61.attention.dense.weight": "model-00031-of-00045.safetensors", + "model.layers.61.attention.query_key_value.weight": "model-00031-of-00045.safetensors", + "model.layers.61.input_layernorm.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.0.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.0.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.0.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.1.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.1.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.1.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.10.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.10.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.10.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.11.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.11.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.11.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.12.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.12.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.12.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.13.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.13.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.13.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.14.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.14.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.14.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.15.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.15.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.15.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.16.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.16.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.16.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.17.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.17.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.17.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.18.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.18.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.18.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.19.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.19.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.19.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.2.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.2.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.2.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.20.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.20.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.20.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.21.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.21.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.21.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.22.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.22.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.22.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.23.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.23.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.23.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.24.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.24.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.24.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.25.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.25.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.25.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.26.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.26.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.26.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.27.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.27.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.27.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.28.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.28.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.28.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.29.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.29.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.29.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.3.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.3.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.3.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.30.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.30.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.30.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.31.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.31.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.31.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.32.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.32.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.32.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.33.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.33.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.33.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.34.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.34.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.34.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.35.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.35.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.35.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.36.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.36.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.36.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.37.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.37.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.37.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.38.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.38.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.38.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.39.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.39.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.39.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.4.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.4.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.4.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.40.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.40.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.40.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.41.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.41.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.41.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.42.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.42.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.42.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.43.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.43.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.43.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.44.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.44.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.44.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.45.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.45.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.45.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.46.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.46.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.46.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.47.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.47.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.47.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.48.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.48.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.48.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.49.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.49.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.49.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.5.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.5.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.5.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.50.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.50.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.50.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.51.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.51.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.51.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.52.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.52.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.52.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.53.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.53.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.53.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.54.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.54.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.54.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.55.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.55.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.55.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.56.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.56.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.56.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.57.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.57.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.57.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.58.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.58.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.58.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.59.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.59.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.59.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.6.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.6.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.6.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.60.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.60.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.60.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.61.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.61.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.61.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.62.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.62.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.62.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.63.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.63.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.63.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.7.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.7.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.7.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.8.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.8.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.8.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.9.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.9.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.experts.9.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.gate.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.weight": "model-00031-of-00045.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00031-of-00045.safetensors", + "model.layers.62.attention.dense.weight": "model-00032-of-00045.safetensors", + "model.layers.62.attention.query_key_value.weight": "model-00032-of-00045.safetensors", + "model.layers.62.input_layernorm.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.0.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.0.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.0.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.1.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.1.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.1.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.10.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.10.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.10.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.11.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.11.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.11.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.12.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.12.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.12.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.13.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.13.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.13.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.14.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.14.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.14.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.15.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.15.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.15.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.16.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.16.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.16.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.17.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.17.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.17.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.18.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.18.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.18.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.19.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.19.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.19.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.2.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.2.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.2.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.20.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.20.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.20.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.21.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.21.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.21.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.22.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.22.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.22.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.23.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.23.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.23.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.24.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.24.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.24.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.25.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.25.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.25.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.26.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.26.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.26.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.27.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.27.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.27.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.28.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.28.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.28.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.29.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.29.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.29.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.3.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.3.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.3.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.30.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.30.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.30.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.31.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.31.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.31.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.32.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.32.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.32.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.33.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.33.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.33.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.34.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.34.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.34.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.35.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.35.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.35.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.36.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.36.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.36.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.37.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.37.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.37.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.38.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.38.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.38.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.39.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.39.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.39.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.4.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.4.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.4.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.40.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.40.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.40.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.41.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.41.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.41.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.42.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.42.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.42.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.43.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.43.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.43.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.44.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.44.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.44.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.45.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.45.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.45.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.46.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.46.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.46.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.47.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.47.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.47.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.48.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.48.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.48.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.49.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.49.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.49.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.5.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.5.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.5.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.50.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.50.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.50.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.51.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.51.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.51.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.52.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.52.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.52.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.53.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.53.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.53.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.54.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.54.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.54.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.55.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.55.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.55.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.56.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.56.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.56.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.57.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.57.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.57.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.58.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.58.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.58.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.59.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.59.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.59.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.6.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.6.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.6.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.60.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.60.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.60.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.61.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.61.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.61.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.62.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.62.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.62.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.63.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.63.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.63.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.7.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.7.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.7.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.8.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.8.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.8.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.9.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.9.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.experts.9.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.gate.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00032-of-00045.safetensors", + "model.layers.63.attention.dense.weight": "model-00032-of-00045.safetensors", + "model.layers.63.attention.query_key_value.weight": "model-00032-of-00045.safetensors", + "model.layers.63.input_layernorm.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.0.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.0.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.0.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.1.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.1.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.1.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.10.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.10.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.10.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.11.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.11.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.11.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.12.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.12.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.12.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.13.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.13.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.13.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.14.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.14.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.14.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.15.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.15.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.15.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.16.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.16.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.16.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.17.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.17.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.17.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.18.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.18.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.18.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.19.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.19.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.19.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.2.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.2.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.2.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.20.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.20.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.20.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.21.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.21.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.21.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.22.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.22.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.22.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.23.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.23.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.23.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.24.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.24.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.24.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.25.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.25.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.25.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.26.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.26.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.26.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.27.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.27.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.27.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.28.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.28.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.28.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.29.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.29.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.29.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.3.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.3.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.3.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.30.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.30.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.30.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.31.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.31.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.31.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.32.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.32.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.32.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.33.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.33.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.33.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.34.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.34.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.34.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.35.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.35.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.35.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.36.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.36.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.36.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.37.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.37.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.37.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.38.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.38.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.38.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.39.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.39.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.39.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.4.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.4.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.4.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.40.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.40.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.40.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.41.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.41.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.41.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.42.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.42.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.42.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.43.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.43.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.43.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.44.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.44.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.44.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.45.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.45.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.45.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.46.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.46.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.46.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.47.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.47.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.47.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.48.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.48.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.48.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.49.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.49.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.49.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.5.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.5.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.5.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.50.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.50.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.50.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.51.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.51.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.51.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.52.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.52.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.52.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.53.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.53.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.53.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.54.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.54.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.54.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.55.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.55.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.55.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.56.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.56.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.56.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.57.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.57.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.57.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.58.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.58.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.58.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.59.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.59.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.59.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.6.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.6.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.6.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.60.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.60.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.60.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.61.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.61.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.61.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.62.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.62.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.62.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.63.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.63.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.63.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.7.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.7.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.7.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.8.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.8.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.8.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.9.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.9.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.experts.9.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.gate.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.weight": "model-00032-of-00045.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00032-of-00045.safetensors", + "model.layers.64.attention.dense.weight": "model-00033-of-00045.safetensors", + "model.layers.64.attention.query_key_value.weight": "model-00033-of-00045.safetensors", + "model.layers.64.input_layernorm.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.0.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.0.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.0.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.1.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.1.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.1.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.10.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.10.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.10.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.11.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.11.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.11.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.12.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.12.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.12.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.13.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.13.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.13.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.14.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.14.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.14.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.15.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.15.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.15.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.16.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.16.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.16.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.17.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.17.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.17.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.18.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.18.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.18.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.19.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.19.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.19.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.2.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.2.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.2.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.20.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.20.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.20.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.21.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.21.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.21.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.22.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.22.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.22.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.23.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.23.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.23.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.24.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.24.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.24.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.25.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.25.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.25.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.26.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.26.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.26.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.27.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.27.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.27.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.28.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.28.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.28.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.29.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.29.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.29.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.3.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.3.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.3.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.30.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.30.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.30.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.31.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.31.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.31.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.32.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.32.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.32.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.33.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.33.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.33.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.34.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.34.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.34.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.35.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.35.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.35.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.36.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.36.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.36.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.37.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.37.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.37.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.38.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.38.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.38.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.39.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.39.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.39.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.4.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.4.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.4.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.40.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.40.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.40.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.41.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.41.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.41.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.42.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.42.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.42.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.43.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.43.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.43.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.44.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.44.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.44.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.45.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.45.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.45.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.46.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.46.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.46.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.47.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.47.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.47.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.48.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.48.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.48.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.49.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.49.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.49.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.5.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.5.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.5.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.50.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.50.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.50.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.51.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.51.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.51.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.52.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.52.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.52.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.53.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.53.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.53.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.54.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.54.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.54.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.55.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.55.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.55.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.56.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.56.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.56.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.57.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.57.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.57.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.58.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.58.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.58.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.59.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.59.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.59.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.6.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.6.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.6.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.60.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.60.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.60.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.61.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.61.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.61.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.62.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.62.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.62.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.63.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.63.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.63.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.7.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.7.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.7.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.8.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.8.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.8.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.9.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.9.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.experts.9.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.gate.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00033-of-00045.safetensors", + "model.layers.65.attention.dense.weight": "model-00033-of-00045.safetensors", + "model.layers.65.attention.query_key_value.weight": "model-00033-of-00045.safetensors", + "model.layers.65.input_layernorm.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.0.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.0.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.0.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.1.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.1.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.1.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.10.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.10.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.10.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.11.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.11.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.11.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.12.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.12.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.12.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.13.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.13.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.13.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.14.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.14.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.14.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.15.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.15.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.15.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.16.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.16.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.16.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.17.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.17.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.17.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.18.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.18.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.18.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.19.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.19.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.19.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.2.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.2.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.2.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.20.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.20.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.20.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.21.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.21.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.21.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.22.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.22.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.22.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.23.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.23.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.23.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.24.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.24.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.24.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.25.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.25.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.25.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.26.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.26.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.26.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.27.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.27.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.27.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.28.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.28.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.28.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.29.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.29.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.29.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.3.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.3.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.3.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.30.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.30.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.30.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.31.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.31.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.31.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.32.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.32.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.32.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.33.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.33.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.33.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.34.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.34.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.34.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.35.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.35.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.35.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.36.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.36.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.36.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.37.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.37.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.37.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.38.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.38.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.38.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.39.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.39.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.39.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.4.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.4.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.4.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.40.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.40.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.40.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.41.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.41.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.41.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.42.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.42.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.42.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.43.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.43.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.43.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.44.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.44.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.44.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.45.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.45.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.45.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.46.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.46.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.46.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.47.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.47.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.47.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.48.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.48.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.48.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.49.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.49.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.49.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.5.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.5.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.5.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.50.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.50.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.50.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.51.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.51.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.51.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.52.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.52.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.52.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.53.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.53.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.53.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.54.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.54.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.54.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.55.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.55.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.55.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.56.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.56.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.56.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.57.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.57.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.57.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.58.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.58.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.58.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.59.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.59.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.59.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.6.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.6.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.6.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.60.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.60.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.60.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.61.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.61.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.61.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.62.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.62.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.62.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.63.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.63.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.63.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.7.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.7.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.7.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.8.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.8.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.8.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.9.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.9.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.experts.9.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.gate.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.weight": "model-00033-of-00045.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00033-of-00045.safetensors", + "model.layers.66.attention.dense.weight": "model-00034-of-00045.safetensors", + "model.layers.66.attention.query_key_value.weight": "model-00034-of-00045.safetensors", + "model.layers.66.input_layernorm.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.0.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.0.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.0.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.1.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.1.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.1.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.10.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.10.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.10.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.11.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.11.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.11.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.12.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.12.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.12.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.13.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.13.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.13.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.14.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.14.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.14.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.15.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.15.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.15.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.16.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.16.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.16.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.17.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.17.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.17.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.18.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.18.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.18.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.19.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.19.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.19.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.2.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.2.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.2.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.20.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.20.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.20.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.21.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.21.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.21.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.22.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.22.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.22.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.23.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.23.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.23.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.24.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.24.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.24.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.25.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.25.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.25.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.26.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.26.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.26.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.27.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.27.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.27.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.28.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.28.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.28.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.29.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.29.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.29.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.3.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.3.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.3.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.30.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.30.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.30.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.31.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.31.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.31.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.32.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.32.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.32.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.33.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.33.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.33.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.34.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.34.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.34.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.35.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.35.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.35.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.36.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.36.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.36.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.37.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.37.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.37.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.38.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.38.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.38.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.39.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.39.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.39.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.4.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.4.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.4.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.40.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.40.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.40.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.41.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.41.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.41.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.42.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.42.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.42.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.43.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.43.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.43.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.44.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.44.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.44.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.45.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.45.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.45.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.46.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.46.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.46.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.47.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.47.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.47.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.48.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.48.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.48.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.49.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.49.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.49.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.5.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.5.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.5.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.50.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.50.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.50.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.51.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.51.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.51.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.52.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.52.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.52.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.53.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.53.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.53.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.54.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.54.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.54.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.55.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.55.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.55.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.56.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.56.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.56.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.57.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.57.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.57.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.58.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.58.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.58.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.59.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.59.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.59.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.6.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.6.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.6.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.60.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.60.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.60.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.61.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.61.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.61.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.62.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.62.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.62.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.63.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.63.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.63.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.7.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.7.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.7.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.8.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.8.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.8.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.9.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.9.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.experts.9.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.gate.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00034-of-00045.safetensors", + "model.layers.67.attention.dense.weight": "model-00034-of-00045.safetensors", + "model.layers.67.attention.query_key_value.weight": "model-00034-of-00045.safetensors", + "model.layers.67.input_layernorm.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.0.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.0.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.0.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.1.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.1.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.1.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.10.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.10.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.10.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.11.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.11.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.11.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.12.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.12.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.12.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.13.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.13.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.13.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.14.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.14.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.14.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.15.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.15.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.15.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.16.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.16.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.16.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.17.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.17.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.17.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.18.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.18.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.18.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.19.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.19.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.19.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.2.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.2.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.2.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.20.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.20.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.20.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.21.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.21.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.21.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.22.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.22.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.22.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.23.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.23.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.23.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.24.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.24.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.24.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.25.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.25.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.25.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.26.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.26.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.26.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.27.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.27.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.27.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.28.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.28.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.28.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.29.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.29.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.29.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.3.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.3.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.3.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.30.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.30.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.30.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.31.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.31.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.31.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.32.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.32.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.32.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.33.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.33.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.33.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.34.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.34.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.34.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.35.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.35.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.35.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.36.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.36.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.36.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.37.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.37.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.37.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.38.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.38.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.38.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.39.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.39.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.39.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.4.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.4.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.4.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.40.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.40.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.40.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.41.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.41.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.41.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.42.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.42.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.42.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.43.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.43.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.43.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.44.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.44.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.44.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.45.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.45.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.45.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.46.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.46.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.46.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.47.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.47.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.47.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.48.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.48.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.48.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.49.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.49.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.49.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.5.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.5.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.5.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.50.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.50.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.50.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.51.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.51.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.51.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.52.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.52.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.52.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.53.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.53.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.53.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.54.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.54.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.54.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.55.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.55.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.55.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.56.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.56.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.56.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.57.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.57.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.57.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.58.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.58.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.58.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.59.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.59.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.59.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.6.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.6.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.6.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.60.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.60.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.60.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.61.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.61.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.61.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.62.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.62.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.62.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.63.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.63.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.63.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.7.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.7.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.7.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.8.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.8.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.8.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.9.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.9.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.experts.9.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.gate.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.weight": "model-00034-of-00045.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00034-of-00045.safetensors", + "model.layers.68.attention.dense.weight": "model-00035-of-00045.safetensors", + "model.layers.68.attention.query_key_value.weight": "model-00035-of-00045.safetensors", + "model.layers.68.input_layernorm.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.0.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.0.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.0.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.1.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.1.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.1.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.10.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.10.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.10.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.11.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.11.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.11.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.12.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.12.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.12.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.13.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.13.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.13.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.14.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.14.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.14.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.15.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.15.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.15.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.16.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.16.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.16.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.17.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.17.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.17.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.18.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.18.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.18.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.19.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.19.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.19.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.2.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.2.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.2.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.20.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.20.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.20.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.21.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.21.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.21.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.22.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.22.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.22.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.23.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.23.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.23.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.24.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.24.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.24.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.25.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.25.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.25.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.26.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.26.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.26.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.27.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.27.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.27.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.28.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.28.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.28.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.29.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.29.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.29.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.3.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.3.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.3.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.30.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.30.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.30.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.31.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.31.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.31.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.32.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.32.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.32.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.33.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.33.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.33.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.34.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.34.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.34.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.35.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.35.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.35.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.36.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.36.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.36.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.37.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.37.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.37.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.38.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.38.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.38.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.39.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.39.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.39.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.4.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.4.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.4.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.40.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.40.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.40.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.41.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.41.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.41.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.42.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.42.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.42.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.43.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.43.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.43.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.44.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.44.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.44.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.45.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.45.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.45.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.46.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.46.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.46.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.47.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.47.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.47.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.48.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.48.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.48.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.49.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.49.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.49.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.5.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.5.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.5.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.50.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.50.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.50.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.51.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.51.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.51.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.52.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.52.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.52.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.53.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.53.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.53.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.54.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.54.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.54.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.55.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.55.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.55.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.56.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.56.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.56.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.57.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.57.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.57.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.58.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.58.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.58.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.59.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.59.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.59.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.6.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.6.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.6.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.60.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.60.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.60.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.61.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.61.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.61.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.62.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.62.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.62.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.63.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.63.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.63.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.7.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.7.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.7.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.8.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.8.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.8.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.9.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.9.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.experts.9.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.gate.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00035-of-00045.safetensors", + "model.layers.69.attention.dense.weight": "model-00035-of-00045.safetensors", + "model.layers.69.attention.query_key_value.weight": "model-00035-of-00045.safetensors", + "model.layers.69.input_layernorm.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.0.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.0.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.0.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.1.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.1.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.1.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.10.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.10.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.10.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.11.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.11.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.11.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.12.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.12.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.12.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.13.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.13.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.13.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.14.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.14.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.14.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.15.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.15.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.15.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.16.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.16.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.16.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.17.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.17.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.17.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.18.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.18.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.18.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.19.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.19.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.19.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.2.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.2.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.2.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.20.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.20.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.20.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.21.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.21.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.21.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.22.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.22.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.22.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.23.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.23.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.23.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.24.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.24.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.24.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.25.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.25.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.25.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.26.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.26.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.26.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.27.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.27.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.27.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.28.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.28.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.28.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.29.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.29.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.29.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.3.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.3.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.3.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.30.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.30.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.30.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.31.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.31.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.31.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.32.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.32.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.32.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.33.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.33.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.33.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.34.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.34.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.34.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.35.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.35.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.35.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.36.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.36.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.36.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.37.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.37.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.37.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.38.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.38.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.38.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.39.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.39.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.39.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.4.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.4.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.4.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.40.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.40.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.40.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.41.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.41.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.41.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.42.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.42.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.42.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.43.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.43.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.43.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.44.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.44.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.44.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.45.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.45.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.45.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.46.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.46.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.46.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.47.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.47.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.47.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.48.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.48.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.48.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.49.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.49.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.49.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.5.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.5.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.5.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.50.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.50.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.50.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.51.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.51.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.51.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.52.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.52.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.52.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.53.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.53.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.53.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.54.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.54.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.54.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.55.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.55.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.55.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.56.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.56.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.56.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.57.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.57.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.57.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.58.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.58.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.58.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.59.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.59.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.59.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.6.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.6.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.6.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.60.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.60.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.60.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.61.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.61.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.61.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.62.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.62.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.62.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.63.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.63.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.63.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.7.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.7.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.7.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.8.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.8.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.8.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.9.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.9.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.experts.9.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.gate.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.weight": "model-00035-of-00045.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00035-of-00045.safetensors", + "model.layers.70.attention.dense.weight": "model-00036-of-00045.safetensors", + "model.layers.70.attention.query_key_value.weight": "model-00036-of-00045.safetensors", + "model.layers.70.input_layernorm.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.0.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.0.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.0.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.1.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.1.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.1.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.10.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.10.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.10.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.11.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.11.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.11.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.12.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.12.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.12.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.13.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.13.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.13.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.14.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.14.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.14.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.15.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.15.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.15.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.16.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.16.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.16.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.17.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.17.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.17.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.18.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.18.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.18.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.19.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.19.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.19.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.2.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.2.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.2.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.20.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.20.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.20.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.21.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.21.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.21.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.22.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.22.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.22.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.23.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.23.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.23.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.24.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.24.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.24.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.25.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.25.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.25.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.26.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.26.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.26.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.27.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.27.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.27.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.28.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.28.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.28.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.29.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.29.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.29.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.3.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.3.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.3.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.30.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.30.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.30.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.31.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.31.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.31.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.32.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.32.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.32.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.33.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.33.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.33.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.34.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.34.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.34.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.35.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.35.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.35.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.36.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.36.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.36.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.37.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.37.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.37.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.38.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.38.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.38.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.39.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.39.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.39.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.4.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.4.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.4.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.40.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.40.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.40.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.41.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.41.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.41.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.42.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.42.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.42.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.43.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.43.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.43.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.44.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.44.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.44.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.45.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.45.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.45.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.46.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.46.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.46.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.47.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.47.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.47.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.48.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.48.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.48.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.49.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.49.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.49.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.5.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.5.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.5.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.50.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.50.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.50.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.51.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.51.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.51.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.52.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.52.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.52.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.53.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.53.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.53.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.54.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.54.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.54.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.55.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.55.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.55.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.56.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.56.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.56.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.57.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.57.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.57.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.58.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.58.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.58.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.59.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.59.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.59.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.6.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.6.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.6.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.60.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.60.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.60.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.61.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.61.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.61.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.62.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.62.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.62.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.63.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.63.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.63.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.7.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.7.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.7.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.8.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.8.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.8.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.9.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.9.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.experts.9.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.gate.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00036-of-00045.safetensors", + "model.layers.71.attention.dense.weight": "model-00036-of-00045.safetensors", + "model.layers.71.attention.query_key_value.weight": "model-00036-of-00045.safetensors", + "model.layers.71.input_layernorm.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.0.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.0.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.0.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.1.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.1.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.1.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.10.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.10.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.10.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.11.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.11.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.11.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.12.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.12.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.12.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.13.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.13.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.13.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.14.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.14.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.14.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.15.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.15.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.15.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.16.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.16.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.16.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.17.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.17.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.17.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.18.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.18.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.18.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.19.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.19.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.19.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.2.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.2.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.2.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.20.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.20.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.20.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.21.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.21.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.21.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.22.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.22.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.22.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.23.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.23.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.23.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.24.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.24.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.24.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.25.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.25.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.25.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.26.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.26.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.26.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.27.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.27.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.27.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.28.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.28.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.28.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.29.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.29.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.29.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.3.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.3.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.3.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.30.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.30.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.30.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.31.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.31.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.31.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.32.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.32.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.32.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.33.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.33.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.33.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.34.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.34.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.34.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.35.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.35.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.35.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.36.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.36.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.36.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.37.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.37.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.37.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.38.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.38.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.38.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.39.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.39.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.39.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.4.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.4.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.4.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.40.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.40.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.40.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.41.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.41.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.41.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.42.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.42.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.42.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.43.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.43.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.43.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.44.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.44.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.44.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.45.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.45.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.45.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.46.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.46.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.46.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.47.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.47.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.47.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.48.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.48.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.48.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.49.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.49.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.49.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.5.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.5.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.5.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.50.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.50.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.50.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.51.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.51.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.51.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.52.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.52.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.52.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.53.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.53.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.53.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.54.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.54.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.54.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.55.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.55.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.55.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.56.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.56.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.56.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.57.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.57.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.57.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.58.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.58.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.58.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.59.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.59.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.59.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.6.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.6.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.6.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.60.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.60.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.60.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.61.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.61.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.61.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.62.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.62.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.62.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.63.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.63.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.63.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.7.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.7.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.7.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.8.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.8.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.8.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.9.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.9.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.experts.9.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.gate.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.weight": "model-00036-of-00045.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00036-of-00045.safetensors", + "model.layers.72.attention.dense.weight": "model-00037-of-00045.safetensors", + "model.layers.72.attention.query_key_value.weight": "model-00037-of-00045.safetensors", + "model.layers.72.input_layernorm.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.0.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.0.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.0.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.1.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.1.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.1.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.10.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.10.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.10.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.11.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.11.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.11.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.12.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.12.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.12.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.13.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.13.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.13.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.14.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.14.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.14.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.15.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.15.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.15.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.16.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.16.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.16.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.17.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.17.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.17.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.18.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.18.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.18.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.19.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.19.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.19.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.2.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.2.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.2.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.20.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.20.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.20.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.21.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.21.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.21.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.22.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.22.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.22.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.23.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.23.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.23.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.24.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.24.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.24.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.25.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.25.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.25.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.26.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.26.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.26.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.27.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.27.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.27.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.28.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.28.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.28.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.29.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.29.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.29.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.3.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.3.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.3.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.30.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.30.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.30.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.31.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.31.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.31.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.32.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.32.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.32.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.33.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.33.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.33.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.34.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.34.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.34.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.35.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.35.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.35.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.36.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.36.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.36.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.37.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.37.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.37.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.38.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.38.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.38.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.39.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.39.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.39.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.4.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.4.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.4.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.40.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.40.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.40.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.41.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.41.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.41.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.42.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.42.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.42.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.43.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.43.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.43.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.44.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.44.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.44.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.45.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.45.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.45.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.46.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.46.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.46.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.47.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.47.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.47.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.48.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.48.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.48.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.49.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.49.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.49.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.5.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.5.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.5.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.50.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.50.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.50.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.51.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.51.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.51.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.52.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.52.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.52.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.53.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.53.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.53.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.54.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.54.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.54.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.55.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.55.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.55.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.56.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.56.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.56.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.57.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.57.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.57.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.58.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.58.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.58.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.59.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.59.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.59.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.6.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.6.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.6.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.60.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.60.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.60.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.61.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.61.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.61.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.62.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.62.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.62.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.63.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.63.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.63.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.7.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.7.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.7.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.8.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.8.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.8.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.9.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.9.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.experts.9.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.gate.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00037-of-00045.safetensors", + "model.layers.73.attention.dense.weight": "model-00037-of-00045.safetensors", + "model.layers.73.attention.query_key_value.weight": "model-00037-of-00045.safetensors", + "model.layers.73.input_layernorm.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.0.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.0.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.0.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.1.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.1.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.1.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.10.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.10.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.10.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.11.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.11.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.11.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.12.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.12.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.12.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.13.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.13.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.13.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.14.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.14.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.14.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.15.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.15.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.15.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.16.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.16.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.16.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.17.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.17.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.17.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.18.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.18.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.18.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.19.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.19.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.19.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.2.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.2.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.2.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.20.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.20.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.20.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.21.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.21.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.21.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.22.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.22.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.22.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.23.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.23.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.23.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.24.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.24.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.24.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.25.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.25.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.25.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.26.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.26.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.26.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.27.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.27.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.27.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.28.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.28.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.28.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.29.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.29.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.29.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.3.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.3.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.3.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.30.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.30.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.30.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.31.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.31.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.31.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.32.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.32.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.32.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.33.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.33.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.33.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.34.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.34.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.34.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.35.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.35.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.35.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.36.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.36.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.36.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.37.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.37.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.37.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.38.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.38.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.38.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.39.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.39.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.39.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.4.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.4.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.4.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.40.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.40.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.40.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.41.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.41.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.41.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.42.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.42.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.42.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.43.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.43.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.43.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.44.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.44.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.44.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.45.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.45.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.45.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.46.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.46.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.46.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.47.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.47.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.47.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.48.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.48.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.48.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.49.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.49.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.49.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.5.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.5.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.5.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.50.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.50.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.50.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.51.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.51.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.51.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.52.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.52.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.52.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.53.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.53.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.53.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.54.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.54.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.54.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.55.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.55.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.55.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.56.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.56.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.56.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.57.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.57.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.57.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.58.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.58.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.58.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.59.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.59.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.59.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.6.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.6.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.6.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.60.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.60.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.60.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.61.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.61.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.61.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.62.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.62.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.62.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.63.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.63.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.63.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.7.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.7.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.7.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.8.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.8.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.8.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.9.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.9.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.experts.9.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.gate.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.weight": "model-00037-of-00045.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00037-of-00045.safetensors", + "model.layers.74.attention.dense.weight": "model-00038-of-00045.safetensors", + "model.layers.74.attention.query_key_value.weight": "model-00038-of-00045.safetensors", + "model.layers.74.input_layernorm.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.0.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.0.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.0.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.1.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.1.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.1.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.10.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.10.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.10.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.11.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.11.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.11.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.12.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.12.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.12.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.13.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.13.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.13.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.14.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.14.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.14.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.15.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.15.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.15.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.16.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.16.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.16.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.17.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.17.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.17.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.18.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.18.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.18.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.19.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.19.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.19.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.2.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.2.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.2.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.20.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.20.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.20.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.21.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.21.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.21.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.22.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.22.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.22.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.23.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.23.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.23.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.24.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.24.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.24.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.25.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.25.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.25.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.26.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.26.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.26.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.27.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.27.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.27.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.28.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.28.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.28.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.29.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.29.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.29.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.3.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.3.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.3.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.30.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.30.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.30.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.31.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.31.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.31.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.32.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.32.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.32.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.33.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.33.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.33.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.34.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.34.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.34.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.35.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.35.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.35.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.36.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.36.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.36.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.37.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.37.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.37.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.38.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.38.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.38.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.39.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.39.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.39.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.4.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.4.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.4.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.40.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.40.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.40.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.41.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.41.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.41.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.42.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.42.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.42.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.43.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.43.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.43.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.44.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.44.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.44.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.45.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.45.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.45.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.46.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.46.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.46.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.47.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.47.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.47.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.48.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.48.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.48.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.49.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.49.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.49.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.5.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.5.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.5.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.50.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.50.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.50.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.51.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.51.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.51.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.52.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.52.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.52.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.53.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.53.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.53.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.54.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.54.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.54.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.55.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.55.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.55.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.56.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.56.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.56.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.57.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.57.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.57.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.58.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.58.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.58.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.59.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.59.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.59.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.6.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.6.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.6.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.60.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.60.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.60.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.61.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.61.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.61.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.62.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.62.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.62.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.63.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.63.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.63.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.7.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.7.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.7.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.8.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.8.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.8.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.9.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.9.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.experts.9.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.gate.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00038-of-00045.safetensors", + "model.layers.75.attention.dense.weight": "model-00038-of-00045.safetensors", + "model.layers.75.attention.query_key_value.weight": "model-00038-of-00045.safetensors", + "model.layers.75.input_layernorm.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.0.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.0.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.0.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.1.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.1.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.1.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.10.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.10.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.10.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.11.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.11.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.11.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.12.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.12.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.12.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.13.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.13.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.13.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.14.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.14.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.14.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.15.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.15.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.15.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.16.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.16.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.16.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.17.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.17.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.17.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.18.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.18.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.18.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.19.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.19.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.19.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.2.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.2.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.2.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.20.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.20.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.20.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.21.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.21.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.21.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.22.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.22.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.22.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.23.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.23.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.23.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.24.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.24.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.24.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.25.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.25.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.25.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.26.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.26.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.26.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.27.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.27.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.27.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.28.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.28.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.28.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.29.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.29.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.29.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.3.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.3.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.3.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.30.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.30.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.30.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.31.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.31.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.31.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.32.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.32.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.32.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.33.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.33.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.33.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.34.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.34.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.34.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.35.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.35.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.35.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.36.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.36.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.36.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.37.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.37.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.37.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.38.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.38.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.38.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.39.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.39.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.39.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.4.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.4.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.4.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.40.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.40.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.40.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.41.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.41.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.41.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.42.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.42.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.42.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.43.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.43.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.43.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.44.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.44.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.44.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.45.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.45.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.45.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.46.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.46.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.46.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.47.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.47.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.47.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.48.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.48.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.48.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.49.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.49.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.49.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.5.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.5.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.5.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.50.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.50.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.50.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.51.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.51.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.51.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.52.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.52.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.52.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.53.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.53.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.53.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.54.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.54.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.54.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.55.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.55.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.55.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.56.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.56.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.56.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.57.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.57.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.57.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.58.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.58.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.58.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.59.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.59.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.59.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.6.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.6.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.6.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.60.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.60.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.60.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.61.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.61.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.61.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.62.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.62.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.62.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.63.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.63.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.63.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.7.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.7.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.7.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.8.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.8.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.8.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.9.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.9.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.experts.9.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.gate.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.weight": "model-00038-of-00045.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00038-of-00045.safetensors", + "model.layers.76.attention.dense.weight": "model-00039-of-00045.safetensors", + "model.layers.76.attention.query_key_value.weight": "model-00039-of-00045.safetensors", + "model.layers.76.input_layernorm.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.0.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.0.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.0.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.1.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.1.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.1.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.10.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.10.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.10.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.11.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.11.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.11.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.12.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.12.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.12.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.13.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.13.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.13.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.14.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.14.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.14.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.15.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.15.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.15.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.16.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.16.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.16.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.17.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.17.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.17.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.18.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.18.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.18.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.19.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.19.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.19.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.2.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.2.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.2.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.20.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.20.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.20.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.21.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.21.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.21.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.22.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.22.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.22.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.23.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.23.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.23.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.24.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.24.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.24.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.25.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.25.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.25.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.26.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.26.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.26.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.27.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.27.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.27.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.28.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.28.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.28.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.29.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.29.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.29.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.3.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.3.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.3.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.30.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.30.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.30.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.31.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.31.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.31.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.32.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.32.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.32.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.33.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.33.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.33.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.34.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.34.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.34.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.35.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.35.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.35.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.36.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.36.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.36.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.37.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.37.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.37.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.38.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.38.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.38.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.39.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.39.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.39.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.4.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.4.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.4.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.40.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.40.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.40.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.41.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.41.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.41.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.42.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.42.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.42.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.43.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.43.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.43.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.44.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.44.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.44.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.45.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.45.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.45.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.46.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.46.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.46.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.47.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.47.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.47.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.48.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.48.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.48.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.49.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.49.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.49.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.5.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.5.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.5.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.50.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.50.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.50.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.51.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.51.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.51.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.52.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.52.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.52.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.53.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.53.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.53.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.54.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.54.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.54.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.55.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.55.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.55.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.56.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.56.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.56.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.57.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.57.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.57.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.58.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.58.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.58.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.59.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.59.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.59.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.6.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.6.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.6.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.60.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.60.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.60.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.61.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.61.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.61.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.62.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.62.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.62.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.63.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.63.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.63.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.7.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.7.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.7.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.8.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.8.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.8.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.9.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.9.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.experts.9.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.gate.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00039-of-00045.safetensors", + "model.layers.77.attention.dense.weight": "model-00039-of-00045.safetensors", + "model.layers.77.attention.query_key_value.weight": "model-00039-of-00045.safetensors", + "model.layers.77.input_layernorm.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.0.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.0.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.0.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.1.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.1.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.1.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.10.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.10.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.10.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.11.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.11.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.11.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.12.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.12.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.12.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.13.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.13.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.13.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.14.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.14.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.14.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.15.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.15.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.15.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.16.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.16.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.16.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.17.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.17.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.17.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.18.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.18.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.18.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.19.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.19.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.19.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.2.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.2.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.2.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.20.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.20.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.20.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.21.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.21.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.21.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.22.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.22.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.22.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.23.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.23.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.23.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.24.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.24.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.24.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.25.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.25.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.25.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.26.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.26.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.26.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.27.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.27.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.27.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.28.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.28.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.28.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.29.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.29.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.29.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.3.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.3.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.3.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.30.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.30.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.30.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.31.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.31.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.31.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.32.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.32.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.32.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.33.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.33.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.33.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.34.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.34.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.34.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.35.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.35.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.35.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.36.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.36.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.36.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.37.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.37.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.37.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.38.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.38.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.38.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.39.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.39.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.39.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.4.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.4.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.4.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.40.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.40.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.40.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.41.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.41.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.41.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.42.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.42.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.42.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.43.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.43.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.43.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.44.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.44.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.44.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.45.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.45.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.45.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.46.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.46.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.46.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.47.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.47.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.47.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.48.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.48.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.48.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.49.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.49.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.49.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.5.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.5.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.5.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.50.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.50.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.50.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.51.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.51.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.51.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.52.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.52.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.52.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.53.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.53.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.53.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.54.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.54.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.54.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.55.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.55.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.55.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.56.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.56.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.56.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.57.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.57.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.57.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.58.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.58.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.58.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.59.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.59.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.59.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.6.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.6.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.6.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.60.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.60.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.60.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.61.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.61.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.61.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.62.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.62.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.62.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.63.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.63.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.63.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.7.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.7.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.7.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.8.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.8.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.8.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.9.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.9.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.experts.9.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.gate.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.weight": "model-00039-of-00045.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00039-of-00045.safetensors", + "model.layers.78.attention.dense.weight": "model-00040-of-00045.safetensors", + "model.layers.78.attention.query_key_value.weight": "model-00040-of-00045.safetensors", + "model.layers.78.input_layernorm.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.0.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.0.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.0.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.1.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.1.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.1.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.10.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.10.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.10.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.11.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.11.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.11.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.12.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.12.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.12.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.13.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.13.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.13.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.14.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.14.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.14.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.15.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.15.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.15.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.16.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.16.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.16.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.17.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.17.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.17.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.18.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.18.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.18.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.19.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.19.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.19.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.2.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.2.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.2.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.20.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.20.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.20.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.21.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.21.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.21.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.22.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.22.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.22.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.23.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.23.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.23.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.24.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.24.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.24.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.25.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.25.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.25.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.26.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.26.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.26.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.27.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.27.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.27.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.28.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.28.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.28.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.29.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.29.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.29.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.3.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.3.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.3.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.30.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.30.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.30.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.31.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.31.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.31.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.32.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.32.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.32.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.33.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.33.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.33.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.34.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.34.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.34.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.35.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.35.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.35.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.36.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.36.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.36.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.37.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.37.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.37.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.38.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.38.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.38.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.39.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.39.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.39.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.4.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.4.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.4.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.40.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.40.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.40.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.41.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.41.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.41.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.42.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.42.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.42.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.43.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.43.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.43.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.44.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.44.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.44.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.45.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.45.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.45.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.46.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.46.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.46.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.47.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.47.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.47.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.48.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.48.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.48.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.49.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.49.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.49.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.5.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.5.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.5.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.50.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.50.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.50.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.51.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.51.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.51.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.52.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.52.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.52.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.53.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.53.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.53.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.54.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.54.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.54.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.55.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.55.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.55.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.56.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.56.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.56.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.57.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.57.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.57.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.58.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.58.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.58.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.59.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.59.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.59.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.6.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.6.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.6.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.60.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.60.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.60.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.61.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.61.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.61.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.62.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.62.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.62.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.63.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.63.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.63.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.7.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.7.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.7.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.8.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.8.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.8.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.9.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.9.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.experts.9.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.gate.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00040-of-00045.safetensors", + "model.layers.79.attention.dense.weight": "model-00040-of-00045.safetensors", + "model.layers.79.attention.query_key_value.weight": "model-00040-of-00045.safetensors", + "model.layers.79.input_layernorm.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.0.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.0.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.0.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.1.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.1.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.1.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.10.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.10.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.10.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.11.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.11.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.11.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.12.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.12.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.12.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.13.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.13.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.13.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.14.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.14.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.14.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.15.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.15.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.15.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.16.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.16.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.16.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.17.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.17.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.17.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.18.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.18.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.18.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.19.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.19.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.19.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.2.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.2.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.2.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.20.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.20.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.20.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.21.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.21.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.21.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.22.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.22.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.22.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.23.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.23.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.23.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.24.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.24.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.24.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.25.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.25.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.25.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.26.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.26.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.26.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.27.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.27.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.27.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.28.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.28.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.28.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.29.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.29.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.29.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.3.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.3.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.3.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.30.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.30.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.30.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.31.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.31.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.31.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.32.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.32.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.32.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.33.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.33.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.33.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.34.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.34.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.34.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.35.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.35.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.35.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.36.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.36.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.36.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.37.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.37.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.37.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.38.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.38.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.38.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.39.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.39.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.39.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.4.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.4.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.4.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.40.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.40.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.40.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.41.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.41.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.41.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.42.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.42.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.42.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.43.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.43.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.43.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.44.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.44.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.44.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.45.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.45.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.45.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.46.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.46.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.46.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.47.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.47.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.47.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.48.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.48.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.48.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.49.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.49.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.49.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.5.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.5.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.5.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.50.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.50.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.50.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.51.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.51.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.51.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.52.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.52.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.52.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.53.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.53.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.53.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.54.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.54.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.54.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.55.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.55.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.55.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.56.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.56.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.56.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.57.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.57.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.57.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.58.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.58.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.58.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.59.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.59.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.59.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.6.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.6.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.6.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.60.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.60.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.60.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.61.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.61.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.61.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.62.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.62.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.62.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.63.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.63.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.63.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.7.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.7.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.7.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.8.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.8.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.8.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.9.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.9.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.experts.9.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.gate.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.weight": "model-00040-of-00045.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00040-of-00045.safetensors", + "model.layers.80.attention.dense.weight": "model-00041-of-00045.safetensors", + "model.layers.80.attention.query_key_value.weight": "model-00041-of-00045.safetensors", + "model.layers.80.input_layernorm.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.0.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.0.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.0.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.1.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.1.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.1.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.10.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.10.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.10.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.11.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.11.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.11.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.12.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.12.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.12.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.13.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.13.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.13.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.14.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.14.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.14.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.15.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.15.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.15.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.16.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.16.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.16.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.17.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.17.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.17.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.18.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.18.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.18.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.19.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.19.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.19.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.2.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.2.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.2.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.20.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.20.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.20.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.21.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.21.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.21.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.22.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.22.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.22.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.23.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.23.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.23.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.24.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.24.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.24.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.25.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.25.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.25.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.26.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.26.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.26.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.27.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.27.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.27.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.28.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.28.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.28.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.29.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.29.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.29.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.3.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.3.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.3.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.30.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.30.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.30.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.31.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.31.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.31.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.32.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.32.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.32.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.33.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.33.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.33.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.34.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.34.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.34.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.35.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.35.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.35.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.36.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.36.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.36.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.37.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.37.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.37.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.38.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.38.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.38.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.39.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.39.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.39.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.4.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.4.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.4.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.40.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.40.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.40.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.41.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.41.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.41.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.42.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.42.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.42.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.43.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.43.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.43.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.44.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.44.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.44.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.45.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.45.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.45.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.46.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.46.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.46.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.47.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.47.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.47.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.48.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.48.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.48.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.49.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.49.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.49.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.5.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.5.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.5.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.50.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.50.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.50.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.51.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.51.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.51.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.52.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.52.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.52.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.53.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.53.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.53.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.54.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.54.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.54.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.55.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.55.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.55.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.56.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.56.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.56.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.57.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.57.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.57.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.58.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.58.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.58.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.59.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.59.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.59.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.6.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.6.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.6.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.60.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.60.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.60.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.61.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.61.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.61.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.62.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.62.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.62.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.63.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.63.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.63.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.7.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.7.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.7.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.8.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.8.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.8.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.9.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.9.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.experts.9.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.gate.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.80.post_attention_layernorm.weight": "model-00041-of-00045.safetensors", + "model.layers.81.attention.dense.weight": "model-00041-of-00045.safetensors", + "model.layers.81.attention.query_key_value.weight": "model-00041-of-00045.safetensors", + "model.layers.81.input_layernorm.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.0.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.0.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.0.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.1.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.1.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.1.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.10.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.10.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.10.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.11.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.11.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.11.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.12.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.12.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.12.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.13.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.13.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.13.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.14.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.14.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.14.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.15.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.15.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.15.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.16.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.16.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.16.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.17.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.17.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.17.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.18.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.18.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.18.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.19.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.19.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.19.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.2.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.2.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.2.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.20.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.20.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.20.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.21.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.21.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.21.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.22.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.22.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.22.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.23.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.23.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.23.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.24.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.24.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.24.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.25.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.25.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.25.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.26.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.26.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.26.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.27.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.27.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.27.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.28.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.28.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.28.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.29.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.29.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.29.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.3.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.3.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.3.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.30.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.30.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.30.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.31.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.31.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.31.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.32.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.32.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.32.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.33.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.33.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.33.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.34.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.34.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.34.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.35.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.35.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.35.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.36.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.36.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.36.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.37.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.37.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.37.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.38.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.38.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.38.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.39.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.39.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.39.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.4.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.4.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.4.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.40.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.40.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.40.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.41.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.41.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.41.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.42.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.42.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.42.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.43.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.43.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.43.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.44.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.44.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.44.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.45.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.45.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.45.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.46.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.46.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.46.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.47.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.47.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.47.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.48.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.48.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.48.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.49.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.49.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.49.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.5.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.5.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.5.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.50.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.50.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.50.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.51.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.51.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.51.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.52.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.52.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.52.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.53.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.53.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.53.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.54.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.54.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.54.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.55.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.55.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.55.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.56.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.56.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.56.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.57.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.57.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.57.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.58.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.58.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.58.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.59.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.59.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.59.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.6.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.6.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.6.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.60.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.60.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.60.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.61.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.61.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.61.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.62.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.62.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.62.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.63.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.63.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.63.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.7.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.7.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.7.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.8.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.8.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.8.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.9.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.9.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.experts.9.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.gate.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.weight": "model-00041-of-00045.safetensors", + "model.layers.81.post_attention_layernorm.weight": "model-00041-of-00045.safetensors", + "model.layers.82.attention.dense.weight": "model-00042-of-00045.safetensors", + "model.layers.82.attention.query_key_value.weight": "model-00042-of-00045.safetensors", + "model.layers.82.input_layernorm.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.0.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.0.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.0.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.1.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.1.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.1.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.10.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.10.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.10.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.11.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.11.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.11.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.12.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.12.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.12.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.13.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.13.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.13.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.14.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.14.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.14.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.15.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.15.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.15.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.16.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.16.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.16.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.17.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.17.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.17.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.18.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.18.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.18.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.19.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.19.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.19.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.2.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.2.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.2.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.20.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.20.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.20.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.21.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.21.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.21.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.22.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.22.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.22.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.23.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.23.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.23.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.24.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.24.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.24.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.25.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.25.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.25.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.26.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.26.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.26.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.27.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.27.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.27.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.28.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.28.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.28.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.29.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.29.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.29.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.3.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.3.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.3.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.30.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.30.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.30.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.31.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.31.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.31.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.32.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.32.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.32.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.33.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.33.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.33.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.34.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.34.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.34.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.35.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.35.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.35.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.36.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.36.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.36.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.37.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.37.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.37.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.38.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.38.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.38.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.39.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.39.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.39.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.4.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.4.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.4.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.40.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.40.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.40.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.41.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.41.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.41.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.42.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.42.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.42.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.43.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.43.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.43.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.44.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.44.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.44.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.45.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.45.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.45.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.46.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.46.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.46.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.47.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.47.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.47.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.48.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.48.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.48.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.49.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.49.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.49.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.5.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.5.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.5.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.50.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.50.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.50.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.51.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.51.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.51.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.52.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.52.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.52.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.53.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.53.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.53.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.54.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.54.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.54.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.55.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.55.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.55.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.56.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.56.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.56.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.57.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.57.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.57.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.58.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.58.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.58.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.59.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.59.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.59.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.6.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.6.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.6.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.60.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.60.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.60.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.61.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.61.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.61.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.62.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.62.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.62.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.63.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.63.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.63.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.7.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.7.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.7.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.8.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.8.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.8.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.9.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.9.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.experts.9.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.gate.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.82.post_attention_layernorm.weight": "model-00042-of-00045.safetensors", + "model.layers.83.attention.dense.weight": "model-00042-of-00045.safetensors", + "model.layers.83.attention.query_key_value.weight": "model-00042-of-00045.safetensors", + "model.layers.83.input_layernorm.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.0.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.0.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.0.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.1.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.1.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.1.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.10.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.10.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.10.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.11.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.11.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.11.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.12.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.12.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.12.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.13.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.13.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.13.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.14.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.14.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.14.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.15.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.15.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.15.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.16.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.16.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.16.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.17.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.17.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.17.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.18.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.18.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.18.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.19.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.19.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.19.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.2.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.2.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.2.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.20.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.20.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.20.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.21.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.21.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.21.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.22.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.22.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.22.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.23.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.23.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.23.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.24.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.24.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.24.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.25.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.25.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.25.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.26.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.26.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.26.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.27.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.27.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.27.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.28.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.28.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.28.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.29.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.29.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.29.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.3.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.3.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.3.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.30.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.30.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.30.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.31.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.31.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.31.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.32.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.32.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.32.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.33.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.33.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.33.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.34.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.34.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.34.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.35.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.35.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.35.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.36.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.36.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.36.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.37.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.37.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.37.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.38.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.38.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.38.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.39.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.39.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.39.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.4.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.4.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.4.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.40.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.40.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.40.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.41.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.41.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.41.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.42.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.42.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.42.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.43.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.43.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.43.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.44.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.44.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.44.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.45.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.45.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.45.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.46.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.46.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.46.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.47.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.47.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.47.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.48.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.48.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.48.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.49.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.49.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.49.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.5.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.5.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.5.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.50.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.50.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.50.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.51.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.51.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.51.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.52.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.52.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.52.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.53.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.53.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.53.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.54.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.54.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.54.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.55.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.55.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.55.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.56.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.56.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.56.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.57.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.57.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.57.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.58.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.58.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.58.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.59.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.59.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.59.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.6.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.6.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.6.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.60.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.60.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.60.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.61.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.61.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.61.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.62.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.62.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.62.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.63.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.63.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.63.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.7.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.7.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.7.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.8.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.8.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.8.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.9.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.9.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.experts.9.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.gate.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.weight": "model-00042-of-00045.safetensors", + "model.layers.83.post_attention_layernorm.weight": "model-00042-of-00045.safetensors", + "model.layers.84.attention.dense.weight": "model-00043-of-00045.safetensors", + "model.layers.84.attention.query_key_value.weight": "model-00043-of-00045.safetensors", + "model.layers.84.input_layernorm.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.0.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.0.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.0.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.1.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.1.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.1.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.10.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.10.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.10.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.11.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.11.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.11.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.12.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.12.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.12.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.13.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.13.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.13.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.14.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.14.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.14.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.15.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.15.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.15.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.16.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.16.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.16.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.17.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.17.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.17.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.18.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.18.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.18.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.19.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.19.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.19.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.2.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.2.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.2.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.20.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.20.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.20.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.21.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.21.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.21.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.22.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.22.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.22.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.23.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.23.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.23.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.24.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.24.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.24.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.25.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.25.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.25.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.26.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.26.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.26.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.27.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.27.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.27.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.28.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.28.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.28.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.29.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.29.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.29.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.3.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.3.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.3.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.30.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.30.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.30.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.31.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.31.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.31.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.32.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.32.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.32.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.33.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.33.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.33.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.34.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.34.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.34.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.35.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.35.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.35.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.36.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.36.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.36.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.37.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.37.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.37.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.38.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.38.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.38.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.39.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.39.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.39.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.4.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.4.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.4.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.40.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.40.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.40.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.41.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.41.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.41.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.42.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.42.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.42.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.43.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.43.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.43.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.44.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.44.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.44.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.45.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.45.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.45.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.46.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.46.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.46.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.47.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.47.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.47.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.48.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.48.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.48.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.49.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.49.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.49.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.5.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.5.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.5.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.50.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.50.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.50.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.51.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.51.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.51.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.52.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.52.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.52.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.53.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.53.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.53.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.54.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.54.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.54.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.55.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.55.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.55.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.56.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.56.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.56.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.57.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.57.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.57.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.58.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.58.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.58.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.59.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.59.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.59.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.6.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.6.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.6.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.60.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.60.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.60.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.61.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.61.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.61.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.62.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.62.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.62.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.63.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.63.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.63.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.7.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.7.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.7.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.8.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.8.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.8.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.9.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.9.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.experts.9.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.gate.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.84.post_attention_layernorm.weight": "model-00043-of-00045.safetensors", + "model.layers.85.attention.dense.weight": "model-00043-of-00045.safetensors", + "model.layers.85.attention.query_key_value.weight": "model-00043-of-00045.safetensors", + "model.layers.85.input_layernorm.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.0.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.0.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.0.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.1.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.1.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.1.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.10.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.10.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.10.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.11.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.11.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.11.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.12.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.12.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.12.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.13.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.13.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.13.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.14.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.14.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.14.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.15.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.15.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.15.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.16.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.16.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.16.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.17.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.17.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.17.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.18.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.18.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.18.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.19.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.19.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.19.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.2.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.2.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.2.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.20.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.20.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.20.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.21.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.21.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.21.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.22.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.22.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.22.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.23.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.23.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.23.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.24.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.24.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.24.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.25.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.25.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.25.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.26.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.26.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.26.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.27.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.27.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.27.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.28.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.28.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.28.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.29.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.29.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.29.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.3.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.3.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.3.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.30.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.30.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.30.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.31.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.31.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.31.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.32.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.32.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.32.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.33.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.33.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.33.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.34.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.34.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.34.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.35.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.35.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.35.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.36.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.36.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.36.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.37.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.37.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.37.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.38.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.38.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.38.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.39.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.39.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.39.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.4.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.4.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.4.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.40.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.40.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.40.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.41.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.41.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.41.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.42.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.42.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.42.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.43.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.43.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.43.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.44.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.44.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.44.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.45.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.45.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.45.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.46.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.46.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.46.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.47.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.47.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.47.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.48.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.48.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.48.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.49.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.49.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.49.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.5.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.5.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.5.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.50.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.50.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.50.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.51.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.51.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.51.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.52.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.52.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.52.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.53.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.53.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.53.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.54.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.54.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.54.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.55.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.55.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.55.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.56.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.56.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.56.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.57.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.57.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.57.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.58.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.58.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.58.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.59.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.59.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.59.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.6.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.6.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.6.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.60.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.60.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.60.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.61.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.61.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.61.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.62.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.62.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.62.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.63.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.63.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.63.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.7.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.7.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.7.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.8.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.8.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.8.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.9.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.9.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.experts.9.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.gate.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.weight": "model-00043-of-00045.safetensors", + "model.layers.85.post_attention_layernorm.weight": "model-00043-of-00045.safetensors", + "model.layers.86.attention.dense.weight": "model-00044-of-00045.safetensors", + "model.layers.86.attention.query_key_value.weight": "model-00044-of-00045.safetensors", + "model.layers.86.input_layernorm.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.0.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.0.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.0.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.1.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.1.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.1.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.10.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.10.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.10.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.11.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.11.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.11.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.12.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.12.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.12.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.13.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.13.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.13.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.14.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.14.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.14.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.15.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.15.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.15.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.16.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.16.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.16.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.17.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.17.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.17.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.18.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.18.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.18.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.19.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.19.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.19.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.2.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.2.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.2.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.20.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.20.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.20.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.21.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.21.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.21.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.22.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.22.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.22.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.23.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.23.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.23.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.24.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.24.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.24.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.25.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.25.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.25.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.26.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.26.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.26.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.27.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.27.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.27.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.28.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.28.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.28.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.29.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.29.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.29.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.3.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.3.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.3.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.30.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.30.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.30.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.31.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.31.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.31.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.32.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.32.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.32.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.33.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.33.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.33.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.34.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.34.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.34.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.35.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.35.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.35.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.36.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.36.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.36.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.37.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.37.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.37.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.38.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.38.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.38.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.39.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.39.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.39.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.4.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.4.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.4.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.40.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.40.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.40.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.41.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.41.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.41.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.42.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.42.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.42.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.43.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.43.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.43.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.44.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.44.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.44.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.45.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.45.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.45.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.46.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.46.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.46.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.47.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.47.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.47.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.48.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.48.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.48.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.49.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.49.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.49.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.5.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.5.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.5.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.50.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.50.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.50.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.51.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.51.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.51.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.52.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.52.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.52.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.53.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.53.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.53.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.54.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.54.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.54.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.55.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.55.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.55.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.56.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.56.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.56.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.57.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.57.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.57.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.58.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.58.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.58.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.59.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.59.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.59.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.6.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.6.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.6.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.60.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.60.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.60.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.61.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.61.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.61.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.62.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.62.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.62.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.63.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.63.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.63.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.7.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.7.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.7.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.8.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.8.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.8.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.9.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.9.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.experts.9.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.gate.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.86.post_attention_layernorm.weight": "model-00044-of-00045.safetensors", + "model.layers.87.attention.dense.weight": "model-00044-of-00045.safetensors", + "model.layers.87.attention.query_key_value.weight": "model-00044-of-00045.safetensors", + "model.layers.87.input_layernorm.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.0.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.0.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.0.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.1.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.1.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.1.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.10.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.10.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.10.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.11.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.11.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.11.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.12.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.12.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.12.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.13.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.13.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.13.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.14.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.14.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.14.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.15.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.15.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.15.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.16.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.16.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.16.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.17.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.17.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.17.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.18.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.18.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.18.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.19.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.19.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.19.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.2.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.2.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.2.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.20.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.20.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.20.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.21.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.21.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.21.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.22.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.22.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.22.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.23.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.23.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.23.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.24.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.24.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.24.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.25.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.25.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.25.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.26.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.26.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.26.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.27.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.27.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.27.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.28.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.28.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.28.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.29.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.29.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.29.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.3.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.3.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.3.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.30.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.30.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.30.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.31.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.31.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.31.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.32.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.32.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.32.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.33.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.33.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.33.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.34.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.34.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.34.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.35.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.35.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.35.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.36.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.36.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.36.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.37.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.37.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.37.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.38.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.38.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.38.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.39.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.39.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.39.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.4.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.4.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.4.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.40.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.40.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.40.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.41.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.41.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.41.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.42.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.42.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.42.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.43.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.43.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.43.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.44.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.44.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.44.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.45.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.45.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.45.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.46.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.46.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.46.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.47.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.47.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.47.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.48.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.48.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.48.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.49.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.49.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.49.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.5.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.5.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.5.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.50.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.50.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.50.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.51.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.51.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.51.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.52.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.52.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.52.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.53.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.53.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.53.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.54.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.54.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.54.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.55.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.55.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.55.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.56.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.56.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.56.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.57.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.57.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.57.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.58.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.58.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.58.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.59.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.59.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.59.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.6.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.6.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.6.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.60.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.60.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.60.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.61.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.61.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.61.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.62.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.62.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.62.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.63.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.63.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.63.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.7.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.7.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.7.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.8.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.8.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.8.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.9.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.9.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.experts.9.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.gate.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.weight": "model-00044-of-00045.safetensors", + "model.layers.87.post_attention_layernorm.weight": "model-00044-of-00045.safetensors", + "lm_head.weight": "model-00045-of-00045.safetensors", + "model.norm.weight": "model-00045-of-00045.safetensors", + "model.word_embeddings.weight": "model-00045-of-00045.safetensors" } } \ No newline at end of file