{ "metadata": { "ParamSize": 323, "ParamBytes": 9081201152.0, "BitsPerParam": 9.046979540559027 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 1050673152, "records": [ { "name": "lm_head.weight", "shape": [ 128256, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1050673152, "byteOffset": 0 } ], "md5sum": "acaaa0d1fae40667cf6951581c648544" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "94df6ed333fde0dbb6bfe1691fa17364" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 1050673152, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 128256, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1050673152, "byteOffset": 0 } ], "md5sum": "d75c672caa231e7f0c33b49ea425706d" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "17b6e3bfa3634f6b47b27539827ad1f0" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c4b1ff2c673ea184f480b2dc447abae0" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "10fd90c0ebd57bfb5d7d847ee4a6db8d" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "50709d56bc47243fbcd5090d6267b07e" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8aa978e2392da213f8d27fbc9f7101da" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "39378fab4003dce8ff61fbd70738aee3" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "fdeefe6cb5990c66a1f53735bc88a76d" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "6dbc5e5901c7c65535d3d8424f4ba1bb" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4605bc9bc9364ce3811afed7f6279eb3" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b97bb4dcf8cae47f2f81f11961fd7565" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "0c27aa6b784847cdb995dbb48147434c" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "e359be74be6731aace4f255bffaf2c06" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4ff3b33d638fbc789de35b828f4ddbf2" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "def84fd83079140cb7cfb4178ac67e3a" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "6009eff5669ec400f2793c72c32e39ae" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "8f4114f7bbc7a21b20ca674425d31805" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d13928ed0282bb2c68869385d3b8f9ce" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8842c98abab621b9d53e2f9261b75159" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "16d74ec0a9783f83137f6db22ed672e9" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "dced9d7894a234aa55f87c31ec2c8793" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c03b2378a72cb8fc55c12d17e541d4a6" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a3afdf0bfa8df0491290af52ff08728d" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "3cd9b7213db2729501e464fcdacb81b6" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "25683c4bc4e6918161d2e7df8c6617f3" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8efc97ddb7f4f7ed5b49bb4355144099" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c8cb15b304fbbb55435f4199bcd2e6be" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "174a2d7bd81ce377abd745610758a40d" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "323393cc19aba26aa4f874c5036749e6" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "bac572ef0647d05de2f0c352ee2a2252" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "14dc3bb8807eb413d26d26a164873659" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "c0b133fb38ecb4b505f8e794ea593e0b" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "a5f8da5b6aa404ddf262dee8bc16e05c" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "492e1f5059bd28e09165cb73a5ea26fd" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "799427e4f2bf3a5ff8fdb1982c98813e" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "ea98d69ab93e3a4265f1a9d9fd163551" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "197e5366b70018351dde47410e6897e3" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "547b90a732909cc56e0f6edee7ac0fd0" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "4a78e282ed8231e246042ccd3b4c44d4" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "be6e38136677eaee017ab7dc9397e37c" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "c64123d97b4fea7365ca80a000a99fe7" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8cbe5b804e73567a88c6379e918afc07" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "10139de7cb709004131c62972ed1497c" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "c1c241cdb9cec7383d72af9545616d2a" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "144f3fb53bda5a56a18b037a1427e2cf" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "7516d2b3712262001c91a03658dbc3d8" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "5b2f56c4e1001fc49728f82f67835bc4" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "e79acf5186a0719067db77a3c8023503" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "163a59e5bb48207e4f7bdc4993e1e8d2" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "60d05afc14746a7d5ea35ce0e7976a31" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d2156d76356b97c7717c7c6641b1124e" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "f2dad698d45ca57e0a93d4d0ee1904be" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "7a701e68fbef8fea088e83d9d633eea4" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "be46fd38f5c60b11e9eaf4c1eda22b6a" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "9428dab85d3be82e84a8e39385e7ae45" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "72ee15ab6b5ab856a2868eeefca28315" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "b7de47ed9081494e19ffb15edfbb5a74" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0197d7c4c7d93fb9c049e42449438ede" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "83d10f67035eb94ebc0ebec56b19b34a" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "3fe4467ea934ff721192aecc14a12538" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "b48382d2f5c78c57b793fac6e87eefd2" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c7004a8665ca642bb4eccea073fcaf31" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8696079905152fdea4dc7ede254973c5" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "1273b50c0e7430d7b57b26ef0972e9d9" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "fa9d531aea0285d92582a5a686dd974c" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8be6f905d75a5cbccae7030a234fef5e" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "55bf30c710c8075ec9ebcfdc865fa568" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "f0cc21639e48dab64b340ff8d6be086f" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "7aa6ae88f116fece2b144adf21e05d4c" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9129e46b6a3f3545dfff1f12760bb4ee" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c26a24b975ffc3678f38e087a1275a04" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "9c22b9cc8b8456dc83180dcf42a1d0bc" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "86505a742e756c9db06f8ddad723ad96" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "7001b55d8181bf846bfe3185fe86abfa" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8cad816b876c08014628ff8b0d91d959" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "19c2a2c06095911afed82d19f8454f08" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ace475b17186bf0f6d6c7c179654d584" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "eba653be0a86ee4eaf84559e75fe40b1" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "2a645b080fc3a01571695c271ec272a4" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "eb84aca9807058856778feaf6e6c8614" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3fea6b4c4b13e64e1c155510599a0e82" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ea173e06c101300ebd9bca2c70886b33" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "33eb76fb9d0cfe48496b1e19721cd29e" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "ba71265b9196ba2d9246390ab344dc1b" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "1321d0a702a5894d43236004af24b10e" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "20649695c42e8bf29bcf0df1a47437ea" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "aa557c2ed757b17da3c71110de9f2092" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "4ba9f34ae8dd49c31f7db7e01581b93b" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "62b635038eb228f798297c62f57d0572" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "72536650ba082f1f8e352d8c47973acb" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a05802f431c544a732f71c582fc3c402" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "dd778e27ba0787e8c5db9af59d5bed6a" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "975f90591d6c62ea460603ea7305fcc2" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "bab15d300d668109ce7c594a7591c059" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d7ebcfcfc4e6b65d72ebff9044a8a8f3" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "a8f2353231649fd8066643611ced34ed" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "6f8d4eaf597930e6ca5f427d2af9f4d8" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "cd6e53cd711a6ad80d4e1841a746da97" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6b919db4361c051483f16964995a9f51" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "7c920bca94c8e8c8b2345dac59094d91" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "d96c6a96bd7a219806378b4a4bf6c6e7" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d572dfc533fe7b0b4f56b4ce8568061c" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ef1c4e3807d04053d86520236f16a3f6" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "c2d0d27ca178dae4fe5058bc3b3939a6" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "2f445b381730d4e6fdbb6fba2241060c" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "245a915a3a85de9e89c2a1f4bad4bc96" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d91394a730af2b55df3ee6200fc6d636" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "64dbbca1f1cf51aeadd82ffe0670060b" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "eda010d7943a8d5c0cf1288cb2cdf9eb" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "14a0f7c3b6763130034e3f0f2e5f4549" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b6561be2ef05c17ea6016af806347a11" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "03321b27dfa2a035b15bdad271c3c6f4" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "c028e4698d34c1be7163460f03b30509" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "02ae1beea7486d631cbc378d521e8f2c" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e64d3ab521a092fe0fa37be649596da2" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "5b477f1efde3ace2c3177b969f4e6470" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "802ea14dd8e010e163f5edeafca32141" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8b6a038d933d1cd0c3c437a3da63c889" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6e93e3a6a6d402564552597008ae38c0" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "8f8ff2f3dcdee181c5c47271b8657ec0" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 14336 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "c346b823b610747743bcf583a5c46863" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "22eccb78a3ff232a096ae910246067d9" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d7cd9ab067b247c7cadf02f4b95e6f00" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "dccf8e2f3a7b7c41f4cce1290552be06" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 28672, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5bf2277e3399ef33710b832c49ad8ca2" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a27ae0827ec4a3389a190aec8553ed7f" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "cd39adb0a6389bc6e9a772a1740357e4" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 25698560, "records": [ { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 0 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 8192 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8194 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 16386 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24578 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 32770 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 32772 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32774 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 4096 ], "dtype": "e4m3_float8", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 40966 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25206790 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25206792 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25206794 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25214986 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25214988 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25214990 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25223182 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25223184 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25223186 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25231378 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25231380 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25231382 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25239574 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25239576 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25239578 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25247770 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25247772 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25247774 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25255966 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25255968 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25255970 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25264162 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25264164 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25264166 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25272358 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25272360 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25272362 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25280554 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25280556 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25280558 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25288750 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25288752 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25288754 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25296946 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25296948 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25296950 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25305142 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25305144 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25305146 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25313338 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25313340 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25313342 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25321534 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25321536 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25321538 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25329730 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25329732 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25329734 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25337926 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25337928 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25337930 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25346122 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25346124 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25346126 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25354318 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25354320 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25354322 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25362514 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25362516 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25362518 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25370710 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25370712 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25370714 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25378906 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25378908 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25378910 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25387102 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25387104 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25387106 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25395298 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25395300 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25395302 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25403494 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25403496 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25403498 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25411690 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25411692 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25411694 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25419886 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25419888 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25419890 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25428082 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25428084 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25428086 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25436278 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25436280 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25436282 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25444474 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25444476 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25444478 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25452670 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25452672 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25452674 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25460866 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25460868 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25460870 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25469062 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25469064 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25469066 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25477258 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25477260 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25477262 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25485454 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25485456 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25485458 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25493650 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25493652 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25493654 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25501846 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25501848 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25501850 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25501852 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25501854 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25501856 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25510048 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25510050 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25510052 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25518244 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25518246 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25518248 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25526440 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25526442 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25534634 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25542826 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25542828 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25542830 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25551022 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25551024 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25551026 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25559218 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25559220 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25559222 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25567414 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25567416 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25567418 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25575610 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25575612 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25575614 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25583806 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25583808 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25583810 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25592002 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25592004 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25592006 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25600198 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25600200 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25600202 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25608394 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25608396 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25608398 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25616590 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25616592 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25616594 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25624786 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25624788 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25624790 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25632982 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25632984 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25632986 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25641178 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25641180 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25641182 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25649374 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25649376 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25649378 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25657570 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25657572 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25657574 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25665766 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25665768 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25665770 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25673962 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25673964 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25673966 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25682158 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25682160 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25682162 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25690354 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25690356 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25690358 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25698550 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25698552 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25698554 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25698556 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 25698558 } ], "md5sum": "92e36c254dd2d2bc7158d731c8413f02" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 256, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 2 }, { "name": "model.layers.0.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 4 }, { "name": "model.layers.0.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 6 }, { "name": "model.layers.1.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 8 }, { "name": "model.layers.1.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 10 }, { "name": "model.layers.1.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 12 }, { "name": "model.layers.1.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 14 }, { "name": "model.layers.2.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 16 }, { "name": "model.layers.2.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 18 }, { "name": "model.layers.2.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 20 }, { "name": "model.layers.2.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 22 }, { "name": "model.layers.3.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 24 }, { "name": "model.layers.3.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 26 }, { "name": "model.layers.3.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 28 }, { "name": "model.layers.3.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 30 }, { "name": "model.layers.4.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 32 }, { "name": "model.layers.4.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 34 }, { "name": "model.layers.4.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 36 }, { "name": "model.layers.4.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 38 }, { "name": "model.layers.5.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 40 }, { "name": "model.layers.5.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 42 }, { "name": "model.layers.5.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 44 }, { "name": "model.layers.5.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 46 }, { "name": "model.layers.6.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 48 }, { "name": "model.layers.6.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 50 }, { "name": "model.layers.6.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 52 }, { "name": "model.layers.6.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 54 }, { "name": "model.layers.7.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 56 }, { "name": "model.layers.7.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 58 }, { "name": "model.layers.7.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 60 }, { "name": "model.layers.7.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 62 }, { "name": "model.layers.8.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 64 }, { "name": "model.layers.8.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 66 }, { "name": "model.layers.8.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 68 }, { "name": "model.layers.8.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 70 }, { "name": "model.layers.9.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 72 }, { "name": "model.layers.9.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 74 }, { "name": "model.layers.9.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 76 }, { "name": "model.layers.9.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 78 }, { "name": "model.layers.10.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 80 }, { "name": "model.layers.10.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 82 }, { "name": "model.layers.10.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 84 }, { "name": "model.layers.10.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 86 }, { "name": "model.layers.11.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 88 }, { "name": "model.layers.11.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 90 }, { "name": "model.layers.11.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 92 }, { "name": "model.layers.11.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 94 }, { "name": "model.layers.12.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 96 }, { "name": "model.layers.12.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 98 }, { "name": "model.layers.12.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 100 }, { "name": "model.layers.12.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 102 }, { "name": "model.layers.13.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 104 }, { "name": "model.layers.13.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 106 }, { "name": "model.layers.13.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 108 }, { "name": "model.layers.13.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 110 }, { "name": "model.layers.14.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 112 }, { "name": "model.layers.14.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 114 }, { "name": "model.layers.14.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 116 }, { "name": "model.layers.14.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 118 }, { "name": "model.layers.15.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 120 }, { "name": "model.layers.15.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 122 }, { "name": "model.layers.15.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 124 }, { "name": "model.layers.15.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 126 }, { "name": "model.layers.16.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 128 }, { "name": "model.layers.16.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 130 }, { "name": "model.layers.16.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 132 }, { "name": "model.layers.16.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 134 }, { "name": "model.layers.17.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 136 }, { "name": "model.layers.17.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 138 }, { "name": "model.layers.17.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 140 }, { "name": "model.layers.17.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 142 }, { "name": "model.layers.18.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 144 }, { "name": "model.layers.18.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 146 }, { "name": "model.layers.18.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 148 }, { "name": "model.layers.18.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 150 }, { "name": "model.layers.19.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 152 }, { "name": "model.layers.19.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 154 }, { "name": "model.layers.19.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 156 }, { "name": "model.layers.19.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 158 }, { "name": "model.layers.20.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 160 }, { "name": "model.layers.20.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 162 }, { "name": "model.layers.20.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 164 }, { "name": "model.layers.20.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 166 }, { "name": "model.layers.21.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 168 }, { "name": "model.layers.21.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 170 }, { "name": "model.layers.21.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 172 }, { "name": "model.layers.21.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 174 }, { "name": "model.layers.22.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 176 }, { "name": "model.layers.22.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 178 }, { "name": "model.layers.22.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 180 }, { "name": "model.layers.22.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 182 }, { "name": "model.layers.23.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 184 }, { "name": "model.layers.23.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 186 }, { "name": "model.layers.23.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 188 }, { "name": "model.layers.23.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 190 }, { "name": "model.layers.24.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 192 }, { "name": "model.layers.24.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 194 }, { "name": "model.layers.24.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 196 }, { "name": "model.layers.24.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 198 }, { "name": "model.layers.25.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 200 }, { "name": "model.layers.25.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 202 }, { "name": "model.layers.25.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 204 }, { "name": "model.layers.25.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 206 }, { "name": "model.layers.26.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 208 }, { "name": "model.layers.26.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 210 }, { "name": "model.layers.26.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 212 }, { "name": "model.layers.26.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 214 }, { "name": "model.layers.27.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 216 }, { "name": "model.layers.27.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 218 }, { "name": "model.layers.27.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 220 }, { "name": "model.layers.27.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 222 }, { "name": "model.layers.28.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 224 }, { "name": "model.layers.28.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 226 }, { "name": "model.layers.28.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 228 }, { "name": "model.layers.28.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 230 }, { "name": "model.layers.29.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 232 }, { "name": "model.layers.29.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 234 }, { "name": "model.layers.29.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 236 }, { "name": "model.layers.29.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 238 }, { "name": "model.layers.30.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 240 }, { "name": "model.layers.30.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 242 }, { "name": "model.layers.30.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 244 }, { "name": "model.layers.30.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 246 }, { "name": "model.layers.31.self_attn.qkv_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 248 }, { "name": "model.layers.31.self_attn.o_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 250 }, { "name": "model.layers.31.mlp.gate_up_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 252 }, { "name": "model.layers.31.mlp.down_proj.q_calibration_scale", "shape": [ 1 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2, "byteOffset": 254 } ], "md5sum": "163928bdc819c2c30d9959aa4f9adde7" } ] }