diff --git a/model_card/layer_images/layer_0_attention_output_dense.png b/model_card/layer_images/layer_0_attention_output_dense.png index 9d8bb4ebd565ec3fb081ea5de2bb2fcc8c86dfa0..c941003f113d5beaef4f09d31e3732e0a5ddc698 100644 Binary files a/model_card/layer_images/layer_0_attention_output_dense.png and b/model_card/layer_images/layer_0_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_0_attention_self_key.png b/model_card/layer_images/layer_0_attention_self_key.png index ecb2335e58b9c9b913a43780e5404da24ee9eb95..80ed0f1e28d6d22069d3e0ebe6fbb99de761d681 100644 Binary files a/model_card/layer_images/layer_0_attention_self_key.png and b/model_card/layer_images/layer_0_attention_self_key.png differ diff --git a/model_card/layer_images/layer_0_attention_self_query.png b/model_card/layer_images/layer_0_attention_self_query.png index 3d348f80388ff8e80ba4e5720acfd26d375d5689..80ed0f1e28d6d22069d3e0ebe6fbb99de761d681 100644 Binary files a/model_card/layer_images/layer_0_attention_self_query.png and b/model_card/layer_images/layer_0_attention_self_query.png differ diff --git a/model_card/layer_images/layer_0_attention_self_value.png b/model_card/layer_images/layer_0_attention_self_value.png index 5a7c130c370e91b6602b81779d8ad80511e1e3ff..80ed0f1e28d6d22069d3e0ebe6fbb99de761d681 100644 Binary files a/model_card/layer_images/layer_0_attention_self_value.png and b/model_card/layer_images/layer_0_attention_self_value.png differ diff --git a/model_card/layer_images/layer_0_intermediate_dense.png b/model_card/layer_images/layer_0_intermediate_dense.png index 45dec226de52ee99938082726df8618e3887a02a..5b62e1b96b99cddc63dc8c6c6fdd811762680ca6 100644 Binary files a/model_card/layer_images/layer_0_intermediate_dense.png and b/model_card/layer_images/layer_0_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_0_output_dense.png b/model_card/layer_images/layer_0_output_dense.png index a91feb59a6b7b24ac85aabfcd362d2246c9515d9..416bca04f08ca78593938327ec34a05ee22d3a9c 100644 Binary files a/model_card/layer_images/layer_0_output_dense.png and b/model_card/layer_images/layer_0_output_dense.png differ diff --git a/model_card/layer_images/layer_10_attention_output_dense.png b/model_card/layer_images/layer_10_attention_output_dense.png index fef7ab1391b480b137d749717d3dad4ebc13e829..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_10_attention_output_dense.png and b/model_card/layer_images/layer_10_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_10_attention_self_key.png b/model_card/layer_images/layer_10_attention_self_key.png index 3f7151ff5b74893a34b43b2fc993c9a4da5f02ee..02ff741e3bd232cb5bf45385c21f338f564b4f85 100644 Binary files a/model_card/layer_images/layer_10_attention_self_key.png and b/model_card/layer_images/layer_10_attention_self_key.png differ diff --git a/model_card/layer_images/layer_10_attention_self_query.png b/model_card/layer_images/layer_10_attention_self_query.png index 94563c1dd9257e0a2e0947d6ffc203bdaedc5efb..02ff741e3bd232cb5bf45385c21f338f564b4f85 100644 Binary files a/model_card/layer_images/layer_10_attention_self_query.png and b/model_card/layer_images/layer_10_attention_self_query.png differ diff --git a/model_card/layer_images/layer_10_attention_self_value.png b/model_card/layer_images/layer_10_attention_self_value.png index 9163ab084e66f1f732a02eb4692702bfae725fbd..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_10_attention_self_value.png and b/model_card/layer_images/layer_10_attention_self_value.png differ diff --git a/model_card/layer_images/layer_10_intermediate_dense.png b/model_card/layer_images/layer_10_intermediate_dense.png index f74d3f1bdf6b8af18b6cfcdbdc631631b6b4321f..8c232a9bb5a46c4cd67d02f324feaac10032283d 100644 Binary files a/model_card/layer_images/layer_10_intermediate_dense.png and b/model_card/layer_images/layer_10_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_10_output_dense.png b/model_card/layer_images/layer_10_output_dense.png index ead62678638bf03d15a663ccded8e25231a04102..2dfaf551860e894ee207e542f1ab52a886715923 100644 Binary files a/model_card/layer_images/layer_10_output_dense.png and b/model_card/layer_images/layer_10_output_dense.png differ diff --git a/model_card/layer_images/layer_11_attention_output_dense.png b/model_card/layer_images/layer_11_attention_output_dense.png index 2129584a6af5e0a073fd7ee59a99f0d27eb1f949..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_11_attention_output_dense.png and b/model_card/layer_images/layer_11_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_11_attention_self_key.png b/model_card/layer_images/layer_11_attention_self_key.png index 037df1a9e4153fada04330eeb00ca297295c0bb8..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_11_attention_self_key.png and b/model_card/layer_images/layer_11_attention_self_key.png differ diff --git a/model_card/layer_images/layer_11_attention_self_query.png b/model_card/layer_images/layer_11_attention_self_query.png index f2165e6acdedfdb347753eec01ad87de1030ce80..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_11_attention_self_query.png and b/model_card/layer_images/layer_11_attention_self_query.png differ diff --git a/model_card/layer_images/layer_11_attention_self_value.png b/model_card/layer_images/layer_11_attention_self_value.png index a1ce06c99cfd0877a3670c4b61748cf3a9ca0748..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_11_attention_self_value.png and b/model_card/layer_images/layer_11_attention_self_value.png differ diff --git a/model_card/layer_images/layer_11_intermediate_dense.png b/model_card/layer_images/layer_11_intermediate_dense.png index bbd49f39a1b2b4b7481c259ea313d91d697134f8..75cb413d889400a8011de0cfc3d5f93f7d7c9182 100644 Binary files a/model_card/layer_images/layer_11_intermediate_dense.png and b/model_card/layer_images/layer_11_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_11_output_dense.png b/model_card/layer_images/layer_11_output_dense.png index df9e69b60d9edb15bf70fdda7d9edc055fce3799..2dfaf551860e894ee207e542f1ab52a886715923 100644 Binary files a/model_card/layer_images/layer_11_output_dense.png and b/model_card/layer_images/layer_11_output_dense.png differ diff --git a/model_card/layer_images/layer_1_attention_output_dense.png b/model_card/layer_images/layer_1_attention_output_dense.png index 036049cce6248719848d74fae4fd6dca2a18e646..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_1_attention_output_dense.png and b/model_card/layer_images/layer_1_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_1_attention_self_key.png b/model_card/layer_images/layer_1_attention_self_key.png index f4defe45c740948aac8fc60a417cf56b583ec491..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_1_attention_self_key.png and b/model_card/layer_images/layer_1_attention_self_key.png differ diff --git a/model_card/layer_images/layer_1_attention_self_query.png b/model_card/layer_images/layer_1_attention_self_query.png index 727b04e4d4ce8a896bff07211060d95e0822b857..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_1_attention_self_query.png and b/model_card/layer_images/layer_1_attention_self_query.png differ diff --git a/model_card/layer_images/layer_1_attention_self_value.png b/model_card/layer_images/layer_1_attention_self_value.png index da7bac0267ee30ced6edabb6bcb5437716d0ea48..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_1_attention_self_value.png and b/model_card/layer_images/layer_1_attention_self_value.png differ diff --git a/model_card/layer_images/layer_1_intermediate_dense.png b/model_card/layer_images/layer_1_intermediate_dense.png index 6a868a4257dad6cacc872a1634e922a48c642fc6..38d6928b44cf5ebdbeaae53436f9c83f3ae62df5 100644 Binary files a/model_card/layer_images/layer_1_intermediate_dense.png and b/model_card/layer_images/layer_1_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_1_output_dense.png b/model_card/layer_images/layer_1_output_dense.png index ea061f05eb331fa2947742c91eb93f9bdef5270c..b03ea36bfd2cb5c6ba8829d6a909277dac1fccf7 100644 Binary files a/model_card/layer_images/layer_1_output_dense.png and b/model_card/layer_images/layer_1_output_dense.png differ diff --git a/model_card/layer_images/layer_2_attention_output_dense.png b/model_card/layer_images/layer_2_attention_output_dense.png index 0ee24107a8c612b3ddb640a1a07fcddc8c0cc38b..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_2_attention_output_dense.png and b/model_card/layer_images/layer_2_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_2_attention_self_key.png b/model_card/layer_images/layer_2_attention_self_key.png index bab9715f758cf427708e831a436380752eb76c95..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_2_attention_self_key.png and b/model_card/layer_images/layer_2_attention_self_key.png differ diff --git a/model_card/layer_images/layer_2_attention_self_query.png b/model_card/layer_images/layer_2_attention_self_query.png index 2c855835fa92a835950bbf580be5712d0e7ec917..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_2_attention_self_query.png and b/model_card/layer_images/layer_2_attention_self_query.png differ diff --git a/model_card/layer_images/layer_2_attention_self_value.png b/model_card/layer_images/layer_2_attention_self_value.png index 52591f602c9597ae7176638c14375420638aab4c..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_2_attention_self_value.png and b/model_card/layer_images/layer_2_attention_self_value.png differ diff --git a/model_card/layer_images/layer_2_intermediate_dense.png b/model_card/layer_images/layer_2_intermediate_dense.png index 9a5db998e4bfa1a230f71af49d1cf7c7e540a482..d5008cf5468069afde6d70932ad93632460d4cfb 100644 Binary files a/model_card/layer_images/layer_2_intermediate_dense.png and b/model_card/layer_images/layer_2_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_2_output_dense.png b/model_card/layer_images/layer_2_output_dense.png index 2778b69d71fba119d1325cbe1b82d8516c2dee57..acdb278e4fd6537ba80f52e71e8e5ffeac17ac19 100644 Binary files a/model_card/layer_images/layer_2_output_dense.png and b/model_card/layer_images/layer_2_output_dense.png differ diff --git a/model_card/layer_images/layer_3_attention_output_dense.png b/model_card/layer_images/layer_3_attention_output_dense.png index ac723880495627f58c45a2150c686d74bf3ce46f..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_3_attention_output_dense.png and b/model_card/layer_images/layer_3_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_3_attention_self_key.png b/model_card/layer_images/layer_3_attention_self_key.png index db4fe2be3decebe8b1f39e6474df95932e0dc01e..bab2e0a8997a67cb58717f9d934b7736da557582 100644 Binary files a/model_card/layer_images/layer_3_attention_self_key.png and b/model_card/layer_images/layer_3_attention_self_key.png differ diff --git a/model_card/layer_images/layer_3_attention_self_query.png b/model_card/layer_images/layer_3_attention_self_query.png index e6573daedc629354d848f545bcac438e54c328bb..bab2e0a8997a67cb58717f9d934b7736da557582 100644 Binary files a/model_card/layer_images/layer_3_attention_self_query.png and b/model_card/layer_images/layer_3_attention_self_query.png differ diff --git a/model_card/layer_images/layer_3_attention_self_value.png b/model_card/layer_images/layer_3_attention_self_value.png index 1d5b5b5804c2d4761e16566022eac799d57cf8cd..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_3_attention_self_value.png and b/model_card/layer_images/layer_3_attention_self_value.png differ diff --git a/model_card/layer_images/layer_3_intermediate_dense.png b/model_card/layer_images/layer_3_intermediate_dense.png index 7fc2086df6de4740980627b4f151a3a9d0d58c63..3c86cc35696c6e680d356b32f2d8e39b33dbf1d1 100644 Binary files a/model_card/layer_images/layer_3_intermediate_dense.png and b/model_card/layer_images/layer_3_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_3_output_dense.png b/model_card/layer_images/layer_3_output_dense.png index c32120bad5af154e032698ac247b0771c77e6a65..9fd3b9db0fe8641dccb4f29cdfe07f8385f4e81d 100644 Binary files a/model_card/layer_images/layer_3_output_dense.png and b/model_card/layer_images/layer_3_output_dense.png differ diff --git a/model_card/layer_images/layer_4_attention_output_dense.png b/model_card/layer_images/layer_4_attention_output_dense.png index 636070eb0c430a1456add8ae31ff50df76aebc86..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_4_attention_output_dense.png and b/model_card/layer_images/layer_4_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_4_attention_self_key.png b/model_card/layer_images/layer_4_attention_self_key.png index ff98812d28df15b194f034dcb7240c12e8eb2db6..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_4_attention_self_key.png and b/model_card/layer_images/layer_4_attention_self_key.png differ diff --git a/model_card/layer_images/layer_4_attention_self_query.png b/model_card/layer_images/layer_4_attention_self_query.png index a95291ba4caf1c157e1c8d508a037102b91fc08a..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_4_attention_self_query.png and b/model_card/layer_images/layer_4_attention_self_query.png differ diff --git a/model_card/layer_images/layer_4_attention_self_value.png b/model_card/layer_images/layer_4_attention_self_value.png index cc4ad2619a4740bdb861a0c1b584912fd2bebdd5..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_4_attention_self_value.png and b/model_card/layer_images/layer_4_attention_self_value.png differ diff --git a/model_card/layer_images/layer_4_intermediate_dense.png b/model_card/layer_images/layer_4_intermediate_dense.png index ff5cf9a3d01a19b1e728bf41db5892a9ca6f24ca..7f7a363b49629827ab391afd3f7467ce90767f11 100644 Binary files a/model_card/layer_images/layer_4_intermediate_dense.png and b/model_card/layer_images/layer_4_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_4_output_dense.png b/model_card/layer_images/layer_4_output_dense.png index 2c1e18dd0bdf35f9f11a6f68be94d943b2bc4ed6..9fdeca846cbb5faa8d638d385f81046e3b8036c5 100644 Binary files a/model_card/layer_images/layer_4_output_dense.png and b/model_card/layer_images/layer_4_output_dense.png differ diff --git a/model_card/layer_images/layer_5_attention_output_dense.png b/model_card/layer_images/layer_5_attention_output_dense.png index 5b8bbd1949cbe092a236c64f375546b8f9b015b9..c941003f113d5beaef4f09d31e3732e0a5ddc698 100644 Binary files a/model_card/layer_images/layer_5_attention_output_dense.png and b/model_card/layer_images/layer_5_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_5_attention_self_key.png b/model_card/layer_images/layer_5_attention_self_key.png index eb7518d3af5d33d5cee715ecdb11cb738cb40264..bab2e0a8997a67cb58717f9d934b7736da557582 100644 Binary files a/model_card/layer_images/layer_5_attention_self_key.png and b/model_card/layer_images/layer_5_attention_self_key.png differ diff --git a/model_card/layer_images/layer_5_attention_self_query.png b/model_card/layer_images/layer_5_attention_self_query.png index 01ae01fec474f102b1cf8883d3bd3268e63d46cb..bab2e0a8997a67cb58717f9d934b7736da557582 100644 Binary files a/model_card/layer_images/layer_5_attention_self_query.png and b/model_card/layer_images/layer_5_attention_self_query.png differ diff --git a/model_card/layer_images/layer_5_attention_self_value.png b/model_card/layer_images/layer_5_attention_self_value.png index 237c7ea99525d53427f66ed84531aabd6cf9655f..bab2e0a8997a67cb58717f9d934b7736da557582 100644 Binary files a/model_card/layer_images/layer_5_attention_self_value.png and b/model_card/layer_images/layer_5_attention_self_value.png differ diff --git a/model_card/layer_images/layer_5_intermediate_dense.png b/model_card/layer_images/layer_5_intermediate_dense.png index b210607e07a0e564aa60857e0f541968fd6de203..18fb4c75ee98f45be11891ea0cb9ad2320a595d6 100644 Binary files a/model_card/layer_images/layer_5_intermediate_dense.png and b/model_card/layer_images/layer_5_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_5_output_dense.png b/model_card/layer_images/layer_5_output_dense.png index f00d3854b41dec894b325f2faae7ccd059261542..1ac750428781dc0bd2728d7b7a9d1997b0bc1e85 100644 Binary files a/model_card/layer_images/layer_5_output_dense.png and b/model_card/layer_images/layer_5_output_dense.png differ diff --git a/model_card/layer_images/layer_6_attention_output_dense.png b/model_card/layer_images/layer_6_attention_output_dense.png index 3046225c10a7fdaefdb74e6a4041eaaaeffec59b..c941003f113d5beaef4f09d31e3732e0a5ddc698 100644 Binary files a/model_card/layer_images/layer_6_attention_output_dense.png and b/model_card/layer_images/layer_6_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_6_attention_self_key.png b/model_card/layer_images/layer_6_attention_self_key.png index a352db1d83215a4c7a562b65cc037577e113a0dc..80ed0f1e28d6d22069d3e0ebe6fbb99de761d681 100644 Binary files a/model_card/layer_images/layer_6_attention_self_key.png and b/model_card/layer_images/layer_6_attention_self_key.png differ diff --git a/model_card/layer_images/layer_6_attention_self_query.png b/model_card/layer_images/layer_6_attention_self_query.png index c41f55ad1acb3ce0fcf5f1b527decfa7dae8b333..bab2e0a8997a67cb58717f9d934b7736da557582 100644 Binary files a/model_card/layer_images/layer_6_attention_self_query.png and b/model_card/layer_images/layer_6_attention_self_query.png differ diff --git a/model_card/layer_images/layer_6_attention_self_value.png b/model_card/layer_images/layer_6_attention_self_value.png index 731f03cf9c1f08bb85bf70ba7c3893e44f557853..bab2e0a8997a67cb58717f9d934b7736da557582 100644 Binary files a/model_card/layer_images/layer_6_attention_self_value.png and b/model_card/layer_images/layer_6_attention_self_value.png differ diff --git a/model_card/layer_images/layer_6_intermediate_dense.png b/model_card/layer_images/layer_6_intermediate_dense.png index 771a5fa580044717f911362ce77064f06ac9ba67..61e55efdfe94c4f73d61f90d042480fe88cf968a 100644 Binary files a/model_card/layer_images/layer_6_intermediate_dense.png and b/model_card/layer_images/layer_6_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_6_output_dense.png b/model_card/layer_images/layer_6_output_dense.png index a37b774d0dce0dc65bc12b0a066edf7ac26d408a..be03d92044618a26c6a66ff5ed765e5d6fddcfe4 100644 Binary files a/model_card/layer_images/layer_6_output_dense.png and b/model_card/layer_images/layer_6_output_dense.png differ diff --git a/model_card/layer_images/layer_7_attention_output_dense.png b/model_card/layer_images/layer_7_attention_output_dense.png index cbc3051c59c6d6735d08995eb26a4cc4099ff423..c941003f113d5beaef4f09d31e3732e0a5ddc698 100644 Binary files a/model_card/layer_images/layer_7_attention_output_dense.png and b/model_card/layer_images/layer_7_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_7_attention_self_key.png b/model_card/layer_images/layer_7_attention_self_key.png index ca39ff29594a5a1245465f1166edfeb88a8e31c4..2b9cfd7efe4be7c8ca935a94033d69c9f538ac7c 100644 Binary files a/model_card/layer_images/layer_7_attention_self_key.png and b/model_card/layer_images/layer_7_attention_self_key.png differ diff --git a/model_card/layer_images/layer_7_attention_self_query.png b/model_card/layer_images/layer_7_attention_self_query.png index c0296c7f8c9bc1b4c83c63003522f8e6227fe80c..56b3bb6c458f2e32faead0a5d413e19d7106890f 100644 Binary files a/model_card/layer_images/layer_7_attention_self_query.png and b/model_card/layer_images/layer_7_attention_self_query.png differ diff --git a/model_card/layer_images/layer_7_attention_self_value.png b/model_card/layer_images/layer_7_attention_self_value.png index 5624c90f8f0c7abf755ffb63128fe5670658e518..1ad85f30b94e0ff4e68636d4ce07730bd50f87c6 100644 Binary files a/model_card/layer_images/layer_7_attention_self_value.png and b/model_card/layer_images/layer_7_attention_self_value.png differ diff --git a/model_card/layer_images/layer_7_intermediate_dense.png b/model_card/layer_images/layer_7_intermediate_dense.png index be244aadf157dccd9494df37fc9ace5be6454d82..d048e529a485fd7b4fbf41525dcddcd2af2d8dc6 100644 Binary files a/model_card/layer_images/layer_7_intermediate_dense.png and b/model_card/layer_images/layer_7_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_7_output_dense.png b/model_card/layer_images/layer_7_output_dense.png index e8e924ba84fd140283fd50b658d514884ec6e711..a00dd14f36fefdadf6cdef2c59ccd82ac6c47471 100644 Binary files a/model_card/layer_images/layer_7_output_dense.png and b/model_card/layer_images/layer_7_output_dense.png differ diff --git a/model_card/layer_images/layer_8_attention_output_dense.png b/model_card/layer_images/layer_8_attention_output_dense.png index cc9c1b42cd3a1b541acea57722ada7857d300ed9..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_8_attention_output_dense.png and b/model_card/layer_images/layer_8_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_8_attention_self_key.png b/model_card/layer_images/layer_8_attention_self_key.png index 5b5a1b56c32f13fd7f33b328dd9da0b775d73053..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_8_attention_self_key.png and b/model_card/layer_images/layer_8_attention_self_key.png differ diff --git a/model_card/layer_images/layer_8_attention_self_query.png b/model_card/layer_images/layer_8_attention_self_query.png index 2e918761ac324df985fa2547b1218a6f0a831808..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_8_attention_self_query.png and b/model_card/layer_images/layer_8_attention_self_query.png differ diff --git a/model_card/layer_images/layer_8_attention_self_value.png b/model_card/layer_images/layer_8_attention_self_value.png index dbffb1d824b1c4ee515c883a21eb5ba3c5e555fb..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_8_attention_self_value.png and b/model_card/layer_images/layer_8_attention_self_value.png differ diff --git a/model_card/layer_images/layer_8_intermediate_dense.png b/model_card/layer_images/layer_8_intermediate_dense.png index 4bd63ecab574a47fa50eae38a6fdbe421606dae9..75cb413d889400a8011de0cfc3d5f93f7d7c9182 100644 Binary files a/model_card/layer_images/layer_8_intermediate_dense.png and b/model_card/layer_images/layer_8_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_8_output_dense.png b/model_card/layer_images/layer_8_output_dense.png index e2be5359c5adb4a0a3bcd4cb899b18489b3c2507..2dfaf551860e894ee207e542f1ab52a886715923 100644 Binary files a/model_card/layer_images/layer_8_output_dense.png and b/model_card/layer_images/layer_8_output_dense.png differ diff --git a/model_card/layer_images/layer_9_attention_output_dense.png b/model_card/layer_images/layer_9_attention_output_dense.png index 20adc099fa208ae5cafeb4f5c314b5f931184064..32fbc5e4c690bcffa1da7212fb57fa969779bdbb 100644 Binary files a/model_card/layer_images/layer_9_attention_output_dense.png and b/model_card/layer_images/layer_9_attention_output_dense.png differ diff --git a/model_card/layer_images/layer_9_attention_self_key.png b/model_card/layer_images/layer_9_attention_self_key.png index 3c05439553af5586ca6cbcf1e94b3d14733258ef..1ad85f30b94e0ff4e68636d4ce07730bd50f87c6 100644 Binary files a/model_card/layer_images/layer_9_attention_self_key.png and b/model_card/layer_images/layer_9_attention_self_key.png differ diff --git a/model_card/layer_images/layer_9_attention_self_query.png b/model_card/layer_images/layer_9_attention_self_query.png index 864c791d84a5af06b590fd98432507a8f986c785..54cfac2534eb4e1ecedde257eb493fcf4467421a 100644 Binary files a/model_card/layer_images/layer_9_attention_self_query.png and b/model_card/layer_images/layer_9_attention_self_query.png differ diff --git a/model_card/layer_images/layer_9_attention_self_value.png b/model_card/layer_images/layer_9_attention_self_value.png index 15b55f95c4bae0cb99235cf9efe503af4665503a..02ff741e3bd232cb5bf45385c21f338f564b4f85 100644 Binary files a/model_card/layer_images/layer_9_attention_self_value.png and b/model_card/layer_images/layer_9_attention_self_value.png differ diff --git a/model_card/layer_images/layer_9_intermediate_dense.png b/model_card/layer_images/layer_9_intermediate_dense.png index 1fd7934e5b62bca8a95c791a13df542f4875a4aa..75cb413d889400a8011de0cfc3d5f93f7d7c9182 100644 Binary files a/model_card/layer_images/layer_9_intermediate_dense.png and b/model_card/layer_images/layer_9_intermediate_dense.png differ diff --git a/model_card/layer_images/layer_9_output_dense.png b/model_card/layer_images/layer_9_output_dense.png index 3f1c32a02e8cd9653c99f0da600284417e831124..2dfaf551860e894ee207e542f1ab52a886715923 100644 Binary files a/model_card/layer_images/layer_9_output_dense.png and b/model_card/layer_images/layer_9_output_dense.png differ diff --git a/model_card/pruning.svg b/model_card/pruning.svg index 8a12be9e1eb1a41cd455c04dfc0e86e71bdb8c97..ee1e29a727ae7a65b7beb4c63b3b2a7dc7a8258b 100644 --- a/model_card/pruning.svg +++ b/model_card/pruning.svg @@ -1 +1 @@ -43464457455389868875877901234567891011024681012prunedactivePruned Transformer HeadsLayer indexHeads count \ No newline at end of file +43464457455389868875877901234567891011024681012prunedactivePruned Transformer HeadsLayer indexHeads count \ No newline at end of file diff --git a/pytorch_model.bin b/pytorch_model.bin index 8383e99c338572a37f971391698db0ec39bba740..5801e6a1a08d3e81c0472aa8dbecd5081b7e719c 100644 --- a/pytorch_model.bin +++ b/pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b4fd2fee288452567abe021c92e2467101616488ed44967fadafad970dfdfa47 -size 435658487 +oid sha256:ef9707601555d278a72d7ef3489330bdad40f76b8e3b9816d3124e8c6b7cd02a +size 364810487