diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..e2ba547319e49b8e5d35a207d2c7450eb9a770d9 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +baseline/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/baseline/T20260406_Ge59eba20/08_HRBench8K.pkl b/baseline/T20260406_Ge59eba20/08_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..823de566fa7a537c84bb9cb9bce1d56e42320a65 --- /dev/null +++ b/baseline/T20260406_Ge59eba20/08_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bdb10ca9b1f92463cf3fb7667f446247d707132ba8f1e36b9a69179af85c8a4 +size 2861 diff --git a/baseline/T20260406_Ge59eba20/18_HRBench8K.pkl b/baseline/T20260406_Ge59eba20/18_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a1b474cfdf6e209c20ec42b7f7367e66c11815ed --- /dev/null +++ b/baseline/T20260406_Ge59eba20/18_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8ab7c3e6394c8e15d1e5dd5f189c8e7e502b2beefa973ce42f850681c827f41 +size 4810 diff --git a/baseline/T20260406_Ge59eba20/28_HRBench8K.pkl b/baseline/T20260406_Ge59eba20/28_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..42a52a1d438f6cfe365530fe9713bf4490ed271c --- /dev/null +++ b/baseline/T20260406_Ge59eba20/28_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51dabab5e06eb700f5aaf46467494936e0d3b5cc5514f10cc7cd82ae6f7afdb2 +size 3178 diff --git a/baseline/T20260406_Ge59eba20/38_HRBench8K.pkl b/baseline/T20260406_Ge59eba20/38_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..69ae22c0e05d01d12b812ef36a6958a7ef136b14 --- /dev/null +++ b/baseline/T20260406_Ge59eba20/38_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68cb10a8f9adb7f1fa852f6e808541605c38eeaa639c7c370af4ee751e09b92a +size 3370 diff --git a/baseline/T20260406_Ge59eba20/48_HRBench8K.pkl b/baseline/T20260406_Ge59eba20/48_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..38f9abd433be592303be16485a1cc31c2bd08ce9 --- /dev/null +++ b/baseline/T20260406_Ge59eba20/48_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f1dcdb413aad9c3d453c68ce62d9b38402d5e247183d8c35c9d120c1ed86aa +size 3185 diff --git a/baseline/T20260406_Ge59eba20/58_HRBench8K.pkl b/baseline/T20260406_Ge59eba20/58_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..49f369791b00a291cf40d03f930b9be25f19ec8f --- /dev/null +++ b/baseline/T20260406_Ge59eba20/58_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f2789fb63f44263b482b4897185a6aa67b8ee9e5d6e5f2cec0f01528e7b4d30 +size 3247 diff --git a/baseline/T20260406_Ge59eba20/68_HRBench8K.pkl b/baseline/T20260406_Ge59eba20/68_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..572cacbfec32efca80abe618b7cbd7bc6dfd055b --- /dev/null +++ b/baseline/T20260406_Ge59eba20/68_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a1786a5f8aece0fee7c27dd34a073749bc0de2d1965242777aa56178b9a887b +size 3976 diff --git a/baseline/T20260406_Ge59eba20/78_HRBench8K.pkl b/baseline/T20260406_Ge59eba20/78_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..34d52502ceaee9dd63638fed335e88f6cb706c90 --- /dev/null +++ b/baseline/T20260406_Ge59eba20/78_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66671b735c4ad16495304912d8dc56f02cd204c5429e52bbdf0d13bb74a4fedc +size 4254 diff --git a/baseline/T20260410_G598544dc/04_HRBench8K.pkl b/baseline/T20260410_G598544dc/04_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..897a27bedb414aec9eabdd850169ebbbd2ff5ff7 --- /dev/null +++ b/baseline/T20260410_G598544dc/04_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ffba6e4207477ff3d0037a68202ffbecc900a938b6195a9185389b13328e68 +size 1437 diff --git a/baseline/T20260410_G598544dc/14_VStarBench.pkl b/baseline/T20260410_G598544dc/14_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ace4284aee38f3a6c69b108179f71c81f984592e --- /dev/null +++ b/baseline/T20260410_G598544dc/14_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6536437b51b19b7e9cb13600bcd057ca086c730a6619321d71e0adbc83e3247b +size 591 diff --git a/baseline/T20260410_G598544dc/24_VStarBench.pkl b/baseline/T20260410_G598544dc/24_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..227f45d8d84112f3e55d106bf84e35b4bdfeb404 --- /dev/null +++ b/baseline/T20260410_G598544dc/24_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63350200f3c34637d1b5d769d648733b971931439bf42f70a977b440891711c6 +size 829 diff --git a/baseline/T20260410_G598544dc/34_VStarBench.pkl b/baseline/T20260410_G598544dc/34_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..039d424bc6ce3be2486ab45b5de24932b9da6c90 --- /dev/null +++ b/baseline/T20260410_G598544dc/34_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c51a627b0e899c79a31348953ac0fd927f1d37116f4a586d08883ee51a4e733 +size 1301 diff --git a/baseline/T20260412_G598544dc/08_HRBench8K.pkl b/baseline/T20260412_G598544dc/08_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a388ccb5cd86149d625dcf22435009faf1c7c402 --- /dev/null +++ b/baseline/T20260412_G598544dc/08_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c1e22c6e31306d9c0a71bce75c4142fdecf1a1d573bcd537e54a8c9a038e5c +size 395 diff --git a/baseline/T20260412_G598544dc/18_VStarBench.pkl b/baseline/T20260412_G598544dc/18_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..677f165fa758aff21585bbc1834d6ec88e9ddb3e --- /dev/null +++ b/baseline/T20260412_G598544dc/18_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8962222418092794dc7d65133e5abed2c152cb7be8f96a462df5b14a0cb6004 +size 287 diff --git a/baseline/T20260412_G598544dc/28_VStarBench.pkl b/baseline/T20260412_G598544dc/28_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..50b642a3d646acd6950b58f4d7dcdca8efc439a6 --- /dev/null +++ b/baseline/T20260412_G598544dc/28_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aa2c4dbc9ff9a02da727047b46f6a5883389d1c3ffd2b047a045f0cea898d56 +size 509 diff --git a/baseline/T20260412_G598544dc/38_VStarBench.pkl b/baseline/T20260412_G598544dc/38_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f25e61bf51e419cd6dfe075f3c51bfc728f2a9f7 --- /dev/null +++ b/baseline/T20260412_G598544dc/38_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fd3e07ee540962ab3dbe0675219d67fb45de0c6e288bb86c688141f798ff6e +size 527 diff --git a/baseline/T20260412_G598544dc/48_VStarBench.pkl b/baseline/T20260412_G598544dc/48_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..84e947b7566f66721c059745fb62514e790e3475 --- /dev/null +++ b/baseline/T20260412_G598544dc/48_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c69c94f71765be1b68858580e470f2df2accfbb1ddfe28b7ae7dfaf63ff015d +size 443 diff --git a/baseline/T20260412_G598544dc/58_VStarBench.pkl b/baseline/T20260412_G598544dc/58_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..462fcdc79465cce961551529fd710296fea60c87 --- /dev/null +++ b/baseline/T20260412_G598544dc/58_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7feddf60eced63c6685bf81b8e236f971f27e83bd0ae97f2792cf6db8c285bb7 +size 320 diff --git a/baseline/T20260412_G598544dc/68_VStarBench.pkl b/baseline/T20260412_G598544dc/68_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..fb440fecb8b1e35b53718787e801badb61223e51 --- /dev/null +++ b/baseline/T20260412_G598544dc/68_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a36834566b8cd1da408ccd732a9b07081d800284ed6b1b84b5751c9be77ecf +size 336 diff --git a/baseline/T20260412_G598544dc/78_VStarBench.pkl b/baseline/T20260412_G598544dc/78_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..982b2dee081641faf6211806c964c89042fd8b7a --- /dev/null +++ b/baseline/T20260412_G598544dc/78_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6300b85ff34b78cae3849e455fd037049d5eaeebe145fcd0898cd3bd516abfaa +size 792 diff --git a/baseline/T20260417_G46902c17/04_HRBench8K.pkl b/baseline/T20260417_G46902c17/04_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9adecb7c638ef3ac02f46486fcfada4acb00b256 --- /dev/null +++ b/baseline/T20260417_G46902c17/04_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3689a9da11ab9bc01e8ac09d4f724ae9dfb27415c8790e88e610939c4d54f26d +size 5614 diff --git a/baseline/T20260417_G46902c17/14_HRBench8K.pkl b/baseline/T20260417_G46902c17/14_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..295e00323ac1204223f46ccf77c0fd9a7360960b --- /dev/null +++ b/baseline/T20260417_G46902c17/14_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f410f7f33b609bd0677874e22043d940e40f6523f3504c15761996acf850ef67 +size 6682 diff --git a/baseline/T20260418_G46902c17/04_HRBench8K.pkl b/baseline/T20260418_G46902c17/04_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..cfd43ef56ac049b30894fb9cdf447b09adc45e62 --- /dev/null +++ b/baseline/T20260418_G46902c17/04_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34758523961a999de9759c8765ecd010c63327c629dda0a6182150f52e908af8 +size 2000 diff --git a/baseline/T20260418_G46902c17/14_HRBench8K.pkl b/baseline/T20260418_G46902c17/14_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..3216c0b9464e2cea30447645d7b1952cd448c6c2 --- /dev/null +++ b/baseline/T20260418_G46902c17/14_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7aee7d9e10efe40bc77a04fd33384104c19864e8eb3ccacb522f3c4a38331f3 +size 3638 diff --git a/baseline/T20260418_G46902c17/24_HRBench8K.pkl b/baseline/T20260418_G46902c17/24_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..d6c14a3d6edf3f40ca49d88deca8fc9b2e47f2bc --- /dev/null +++ b/baseline/T20260418_G46902c17/24_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4a4ccbacc6ef69ac1096c14a946d166754e68a373afce242061f3e2136d3544 +size 2852 diff --git a/baseline/T20260418_G46902c17/34_HRBench8K.pkl b/baseline/T20260418_G46902c17/34_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c3f426f659d9f4f909397fe02901b9fe3f64c293 --- /dev/null +++ b/baseline/T20260418_G46902c17/34_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbc53bba40036f6b4aa1f3db8db48719a1c9f5c0c98c9a8d2441169df08bfbe7 +size 4339 diff --git a/baseline/T20260423_G2383b931/checkpoint-48_MMVet.xlsx b/baseline/T20260423_G2383b931/checkpoint-48_MMVet.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..86b2db566c8d5f54fb33d697f61b422f8dba6867 Binary files /dev/null and b/baseline/T20260423_G2383b931/checkpoint-48_MMVet.xlsx differ diff --git a/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl b/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl new file mode 100644 index 0000000000000000000000000000000000000000..10bfdd0fcfe5562f15aba6f6140770a20ddff82b --- /dev/null +++ b/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe300004eff941b191c7fc82e55a8e09616d6b0529047e6e1195bb368a8ed88e +size 8979 diff --git a/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx b/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..64535eeeae00a3ebce25bce57833e9a9506e993c Binary files /dev/null and b/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx differ diff --git a/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv b/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv new file mode 100644 index 0000000000000000000000000000000000000000..f61b9bd2e99291c253fa4411774e510950c63fb8 --- /dev/null +++ b/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv @@ -0,0 +1,8 @@ +"Category","tot","acc" +"rec","187","64.59893048128345" +"ocr","108","73.70370370370371" +"know","84","46.07142857142857" +"gen","80","50.125" +"spat","75","68.66666666666666" +"math","26","70.76923076923076" +"Overall","218","64.22018348623857" diff --git a/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv b/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv new file mode 100644 index 0000000000000000000000000000000000000000..05611e108fb7bc9af81d72b74bcffb1e1ff885ac --- /dev/null +++ b/baseline/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv @@ -0,0 +1,18 @@ +"Category","tot","acc" +"ocr_math","11","72.72727272727273" +"ocr_spat_math","14","74.28571428571429" +"rec_ocr_spat_math","1","0.0" +"rec_spat","12","74.16666666666667" +"ocr_spat","26","73.07692307692307" +"rec_ocr_spat","7","42.857142857142854" +"ocr_know_spat","3","66.66666666666666" +"rec_ocr","4","100.0" +"rec_know_spat","2","0.0" +"ocr","108","73.70370370370371" +"rec","187","64.59893048128345" +"rec_know","9","53.333333333333336" +"rec_know_gen","62","40.48387096774195" +"rec_ocr_know_gen","8","85.0" +"rec_ocr_gen_spat","8","85.0" +"ocr_gen_spat","2","70.0" +"Overall","218","64.22018348623857" diff --git a/baseline/T20260423_G2383b931/checkpoint-48_POPE.xlsx b/baseline/T20260423_G2383b931/checkpoint-48_POPE.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..3e40e286d0cb59b699e678e6429355a30ccee1ee Binary files /dev/null and b/baseline/T20260423_G2383b931/checkpoint-48_POPE.xlsx differ diff --git a/baseline/T20260423_G2383b931/checkpoint-48_POPE_auxmatch.xlsx b/baseline/T20260423_G2383b931/checkpoint-48_POPE_auxmatch.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..bc4d1aeae3fb1768651c6e68ad021c8314338489 Binary files /dev/null and b/baseline/T20260423_G2383b931/checkpoint-48_POPE_auxmatch.xlsx differ diff --git a/baseline/T20260423_G2383b931/checkpoint-48_POPE_score.csv b/baseline/T20260423_G2383b931/checkpoint-48_POPE_score.csv new file mode 100644 index 0000000000000000000000000000000000000000..b8490138203c904e2b5516003dc8c8efb5916df9 --- /dev/null +++ b/baseline/T20260423_G2383b931/checkpoint-48_POPE_score.csv @@ -0,0 +1,5 @@ +"split","Overall","acc","precision","recall" +"Overall","87.25099601593625","87.83269961977186","90.87136929460581","83.9080459770115" +"popular","87.4251497005988","88.06818181818183","91.25","83.9080459770115" +"adversarial","84.39306358381502","84.57142857142857","84.88372093023256","83.9080459770115" +"random","90.12345679012346","90.85714285714286","97.33333333333334","83.9080459770115" diff --git a/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA.xlsx b/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..0656f59874211ba86423688d485e85cd2c8dda5a Binary files /dev/null and b/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA.xlsx differ diff --git a/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl b/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..afd3c29ad43adcaa6284815dc93f48a2d03f2f30 --- /dev/null +++ b/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37b36bab627c2045b2635b67f76e001ccaf5cb24ed528d582802d31f9e9022fa +size 17977 diff --git a/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx b/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..bd2b1194f15c96ed129850d0ad5863e320610f46 Binary files /dev/null and b/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx differ diff --git a/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_acc.csv b/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..63ba1871046070a38b511ee5c3e05eb5bdbc1598 --- /dev/null +++ b/baseline/T20260423_G2383b931/checkpoint-48_RealWorldQA_acc.csv @@ -0,0 +1,2 @@ +"split","Overall" +"none","0.7266666666666667" diff --git a/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG.xlsx b/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..7c678a966871b96ac1912964e3cf4a2b56345613 Binary files /dev/null and b/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG.xlsx differ diff --git a/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl b/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..79e2a9af3bfa70215e6fb110223d9c16515ec790 --- /dev/null +++ b/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b9bbfb7dd6744c1930078c6b184e16908630bdf866722c023c3935642f9320 +size 17154 diff --git a/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx b/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..25af5a09fe05246ef271f64b513fd74f9ff13431 Binary files /dev/null and b/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx differ diff --git a/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_acc.csv b/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..c0b09a0914d53d2e6f5545da18b4e6683393fb72 --- /dev/null +++ b/baseline/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_acc.csv @@ -0,0 +1,2 @@ +"split","Overall","Instance Attributes","Instance Identity","Instance Interaction","Instance Location","Instances Counting","Scene Understanding","Spatial Relation","Text Understanding","Visual Reasoning" +"none","0.7533333333333333","0.8041237113402062","0.8269230769230769","1.0","0.6818181818181818","0.7142857142857143","0.7169811320754716","0.42857142857142855","1.0","0.5" diff --git a/baseline/args.json b/baseline/args.json new file mode 100644 index 0000000000000000000000000000000000000000..072e76a252501aea780d7ef3af7fc7a52a411d78 --- /dev/null +++ b/baseline/args.json @@ -0,0 +1,376 @@ +{ + "output_dir": "/raid/icy/Thyme/output_dir/v2-20260406-012551", + "per_device_train_batch_size": 1, + "num_train_epochs": 3.0, + "max_steps": -1, + "learning_rate": 1e-06, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": null, + "warmup_steps": 0, + "optim": "adamw_torch", + "optim_args": null, + "weight_decay": 0.1, + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "optim_target_modules": null, + "gradient_accumulation_steps": 16, + "average_tokens_across_devices": true, + "max_grad_norm": 1.0, + "label_smoothing_factor": 0.0, + "bf16": true, + "fp16": false, + "bf16_full_eval": false, + "fp16_full_eval": false, + "tf32": null, + "gradient_checkpointing": true, + "gradient_checkpointing_kwargs": null, + "torch_compile": false, + "torch_compile_backend": null, + "torch_compile_mode": null, + "use_liger_kernel": false, + "liger_kernel_config": null, + "use_cache": false, + "neftune_noise_alpha": null, + "torch_empty_cache_steps": null, + "auto_find_batch_size": false, + "logging_strategy": "steps", + "logging_steps": 5, + "logging_first_step": true, + "log_on_each_node": true, + "logging_nan_inf_filter": true, + "include_num_input_tokens_seen": false, + "log_level": "passive", + "log_level_replica": "warning", + "disable_tqdm": null, + "report_to": [ + "wandb" + ], + "run_name": "/raid/icy/Thyme/output_dir/v2-20260406-012551", + "project": "huggingface", + "trackio_space_id": "trackio", + "eval_strategy": "no", + "eval_steps": null, + "eval_delay": 0, + "per_device_eval_batch_size": 1, + "prediction_loss_only": false, + "eval_on_start": false, + "eval_do_concat_batches": true, + "eval_use_gather_object": false, + "eval_accumulation_steps": null, + "include_for_metrics": [], + "batch_eval_metrics": false, + "save_only_model": false, + "save_strategy": "epoch", + "save_steps": 500, + "save_on_each_node": false, + "save_total_limit": 1, + "enable_jit_checkpoint": false, + "push_to_hub": false, + "hub_token": null, + "hub_private_repo": null, + "hub_model_id": null, + "hub_strategy": "every_save", + "hub_always_push": false, + "hub_revision": null, + "load_best_model_at_end": false, + "metric_for_best_model": "loss", + "greater_is_better": false, + "ignore_data_skip": false, + "restore_callback_states_from_checkpoint": false, + "full_determinism": false, + "seed": 42, + "data_seed": 42, + "use_cpu": false, + "accelerator_config": { + "dispatch_batches": false + }, + "parallelism_config": null, + "dataloader_drop_last": false, + "dataloader_num_workers": 4, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": false, + "dataloader_prefetch_factor": null, + "remove_unused_columns": true, + "label_names": null, + "train_sampling_strategy": "random", + "length_column_name": "length", + "ddp_find_unused_parameters": null, + "ddp_bucket_cap_mb": null, + "ddp_broadcast_buffers": null, + "ddp_backend": null, + "ddp_timeout": 18000000, + "fsdp": [], + "fsdp_config": null, + "deepspeed": { + "fp16": { + "enabled": "auto", + "loss_scale": 0, + "loss_scale_window": 1000, + "initial_scale_power": 16, + "hysteresis": 2, + "min_loss_scale": 1 + }, + "bf16": { + "enabled": "auto" + }, + "zero_optimization": { + "stage": 1, + "offload_optimizer": { + "device": "none", + "pin_memory": true + }, + "allgather_partitions": true, + "allgather_bucket_size": 200000000.0, + "overlap_comm": false, + "reduce_scatter": true, + "reduce_bucket_size": 200000000.0, + "contiguous_gradients": true + }, + "gradient_accumulation_steps": "auto", + "gradient_clipping": "auto", + "steps_per_print": 2000, + "train_batch_size": "auto", + "train_micro_batch_size_per_gpu": "auto", + "wall_clock_breakdown": false + }, + "debug": null, + "skip_memory_metrics": true, + "do_train": false, + "do_eval": false, + "do_predict": false, + "resume_from_checkpoint": null, + "warmup_ratio": 0.05, + "logging_dir": "/raid/icy/Thyme/output_dir/v2-20260406-012551/runs", + "local_rank": 0, + "sortish_sampler": false, + "predict_with_generate": false, + "generation_max_length": null, + "generation_num_beams": null, + "generation_config": null, + "tuner_backend": "peft", + "vit_gradient_checkpointing": null, + "router_aux_loss_coef": 0.0, + "enable_dft_loss": false, + "enable_channel_loss": false, + "safe_serialization": true, + "max_shard_size": "5GB", + "check_model": true, + "acc_strategy": "token", + "train_dataloader_shuffle": true, + "group_by_length": false, + "max_epochs": null, + "aligner_lr": null, + "vit_lr": null, + "use_logits_to_keep": null, + "ds3_gather_for_generation": true, + "resume_only_model": false, + "optimizer": null, + "loss_type": null, + "eval_metric": null, + "callbacks": [], + "early_stop_interval": null, + "eval_use_evalscope": false, + "eval_dataset": [], + "eval_dataset_args": null, + "eval_limit": null, + "eval_generation_config": null, + "extra_eval_args": null, + "tuner_type": "full", + "use_galore": false, + "galore_target_modules": null, + "galore_rank": 128, + "galore_update_proj_gap": 50, + "galore_scale": 1.0, + "galore_proj_type": "std", + "galore_optim_per_parameter": false, + "galore_with_embedding": false, + "galore_quantization": false, + "galore_proj_quant": false, + "galore_proj_bits": 4, + "galore_proj_group_size": 256, + "galore_cos_threshold": 0.4, + "galore_gamma_proj": 2, + "galore_queue_size": 5, + "lisa_activated_layers": 0, + "lisa_step_interval": 20, + "use_flash_ckpt": false, + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "/raid/icy/Thyme/output_dir/v1-20260406-004513/checkpoint-243", + "model_type": "qwen2_5_vl", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": "flash_attn", + "experts_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": null, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "qwen2_5_vl", + "system": null, + "max_length": 10240, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_side": "right", + "padding_free": false, + "loss_scale": "default", + "sequence_parallel_size": 1, + "template_backend": "swift", + "response_prefix": null, + "enable_thinking": null, + "add_non_thinking_prefix": true, + "dataset": [ + "/raid/icy/data/Thyme_sft_data/jsonl/computation_without_image.jsonl" + ], + "val_dataset": [], + "cached_dataset": [], + "cached_val_dataset": [], + "split_dataset_ratio": 0.0, + "dataset_num_proc": 1, + "load_from_cache_file": false, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": 64, + "temperature": 0.0, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "structured_outputs_regex": null, + "train_type": "full", + "adapters": [], + "external_plugins": [], + "custom_register_path": [], + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": false, + "packing_length": null, + "packing_num_proc": 1, + "lazy_tokenize": true, + "use_hf": false, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_parameters": [ + "model.visual", + "model.visual.merger" + ], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "target_parameters": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "lorap_lr_ratio": null, + "use_rslora": false, + "use_dora": false, + "lora_ga_batch_size": 2, + "lora_ga_iters": 2, + "lora_ga_max_length": 1024, + "lora_ga_direction": "ArB2r", + "lora_ga_scale": "stable", + "lora_ga_stable_gamma": 16, + "init_weights": true, + "fourier_n_frequency": 2000, + "fourier_scaling": 300.0, + "boft_block_size": 4, + "boft_block_num": 0, + "boft_n_butterfly_factor": 1, + "boft_dropout": 0.0, + "vera_rank": 256, + "vera_projection_prng_key": 0, + "vera_dropout": 0.0, + "vera_d_initial": 0.1, + "adapter_act": "gelu", + "adapter_length": 128, + "adalora_target_r": 8, + "adalora_init_r": 12, + "adalora_tinit": 0, + "adalora_tfinal": 0, + "adalora_deltaT": 1, + "adalora_beta1": 0.85, + "adalora_beta2": 0.85, + "adalora_orth_reg_weight": 0.5, + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "reft_layer_key": null, + "reft_layers": null, + "reft_rank": 4, + "reft_intervention_type": "LoreftIntervention", + "reft_args": null, + "swanlab_token": null, + "swanlab_project": "ms-swift", + "swanlab_workspace": null, + "swanlab_exp_name": null, + "swanlab_notification_method": null, + "swanlab_webhook_url": null, + "swanlab_secret": null, + "swanlab_sender_email": null, + "swanlab_receiver_email": null, + "swanlab_smtp_server": null, + "swanlab_smtp_port": null, + "swanlab_email_language": "zh", + "swanlab_mode": "cloud", + "add_version": true, + "create_checkpoint_symlink": false, + "zero_hpz_partition_size": null, + "deepspeed_autotp_size": null, + "swift_version": "4.1.0.dev0", + "ckpt_dir": "/raid/icy/Thyme/output_dir/v1-20260406-004513/checkpoint-243", + "rank": 0, + "global_world_size": 8, + "local_world_size": 8, + "model_suffix": "checkpoint-243", + "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/raid/icy/Thyme/output_dir/v1-20260406-004513/checkpoint-243', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)", + "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], template='qwen2_5_vl', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], template='qwen2_5_vl', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='XiaomiMiMo/MiMo-VL-7B-SFT', hf_model_id='XiaomiMiMo/MiMo-VL-7B-SFT', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='XiaomiMiMo/MiMo-VL-7B-RL', hf_model_id='XiaomiMiMo/MiMo-VL-7B-RL', model_path=None, ms_revision=None, hf_revision=None)], template='mimo_vl', ignore_patterns=None, requires=None, tags=[])], loader=, template=None, model_arch=MultiModelKeys(arch_name='qwen2_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])", + "model_dir": "/raid/icy/Thyme/output_dir/v1-20260406-004513/checkpoint-243", + "template_meta": "QwenTemplateMeta(template_type='qwen2_5_vl', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system='You are a helpful assistant.', auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='', non_thinking_prefix='', history_thinking_prefix='')", + "_val_dataset_exists": false, + "hub": "", + "evaluation_strategy": "epoch", + "training_args": "Seq2SeqTrainingArguments(output_dir='/raid/icy/Thyme/output_dir/v2-20260406-012551', per_device_train_batch_size=1, num_train_epochs=3.0, max_steps=-1, learning_rate=1e-06, lr_scheduler_type=, lr_scheduler_kwargs=None, warmup_steps=0.05, optim=, optim_args=None, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=16, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=, logging_steps=5, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=['wandb'], run_name='/raid/icy/Thyme/output_dir/v2-20260406-012551', project='huggingface', trackio_space_id='trackio', eval_strategy=, eval_steps=None, eval_delay=0, per_device_eval_batch_size=1, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=False, save_strategy=, save_steps=500, save_on_each_node=False, save_total_limit=1, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, dataloader_drop_last=False, dataloader_num_workers=4, dataloader_pin_memory=True, dataloader_persistent_workers=False, dataloader_prefetch_factor=2, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_backend=None, ddp_timeout=18000000, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 1, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, debug=[], skip_memory_metrics=True, do_train=False, do_eval=False, do_predict=False, resume_from_checkpoint=None, warmup_ratio=0.05, logging_dir='/raid/icy/Thyme/output_dir/v2-20260406-012551/runs', local_rank=0, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, group_by_length=False, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)" +} \ No newline at end of file diff --git a/baseline/chat_template.jinja b/baseline/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..6c226632394ae7474b0d4b13e15793eac2e21ee9 --- /dev/null +++ b/baseline/chat_template.jinja @@ -0,0 +1,7 @@ +{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system +You are a helpful assistant.<|im_end|> +{% endif %}<|im_start|>{{ message['role'] }} +{% if message['content'] is string %}{{ message['content'] }}<|im_end|> +{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|> +{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant +{% endif %} \ No newline at end of file diff --git a/baseline/checkpoint-48_MMVet.xlsx b/baseline/checkpoint-48_MMVet.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..86b2db566c8d5f54fb33d697f61b422f8dba6867 Binary files /dev/null and b/baseline/checkpoint-48_MMVet.xlsx differ diff --git a/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl b/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl new file mode 100644 index 0000000000000000000000000000000000000000..10bfdd0fcfe5562f15aba6f6140770a20ddff82b --- /dev/null +++ b/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe300004eff941b191c7fc82e55a8e09616d6b0529047e6e1195bb368a8ed88e +size 8979 diff --git a/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx b/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..64535eeeae00a3ebce25bce57833e9a9506e993c Binary files /dev/null and b/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx differ diff --git a/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv b/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv new file mode 100644 index 0000000000000000000000000000000000000000..f61b9bd2e99291c253fa4411774e510950c63fb8 --- /dev/null +++ b/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv @@ -0,0 +1,8 @@ +"Category","tot","acc" +"rec","187","64.59893048128345" +"ocr","108","73.70370370370371" +"know","84","46.07142857142857" +"gen","80","50.125" +"spat","75","68.66666666666666" +"math","26","70.76923076923076" +"Overall","218","64.22018348623857" diff --git a/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv b/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv new file mode 100644 index 0000000000000000000000000000000000000000..05611e108fb7bc9af81d72b74bcffb1e1ff885ac --- /dev/null +++ b/baseline/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv @@ -0,0 +1,18 @@ +"Category","tot","acc" +"ocr_math","11","72.72727272727273" +"ocr_spat_math","14","74.28571428571429" +"rec_ocr_spat_math","1","0.0" +"rec_spat","12","74.16666666666667" +"ocr_spat","26","73.07692307692307" +"rec_ocr_spat","7","42.857142857142854" +"ocr_know_spat","3","66.66666666666666" +"rec_ocr","4","100.0" +"rec_know_spat","2","0.0" +"ocr","108","73.70370370370371" +"rec","187","64.59893048128345" +"rec_know","9","53.333333333333336" +"rec_know_gen","62","40.48387096774195" +"rec_ocr_know_gen","8","85.0" +"rec_ocr_gen_spat","8","85.0" +"ocr_gen_spat","2","70.0" +"Overall","218","64.22018348623857" diff --git a/baseline/checkpoint-48_POPE.xlsx b/baseline/checkpoint-48_POPE.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..3e40e286d0cb59b699e678e6429355a30ccee1ee Binary files /dev/null and b/baseline/checkpoint-48_POPE.xlsx differ diff --git a/baseline/checkpoint-48_POPE_auxmatch.xlsx b/baseline/checkpoint-48_POPE_auxmatch.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..bc4d1aeae3fb1768651c6e68ad021c8314338489 Binary files /dev/null and b/baseline/checkpoint-48_POPE_auxmatch.xlsx differ diff --git a/baseline/checkpoint-48_POPE_score.csv b/baseline/checkpoint-48_POPE_score.csv new file mode 100644 index 0000000000000000000000000000000000000000..b8490138203c904e2b5516003dc8c8efb5916df9 --- /dev/null +++ b/baseline/checkpoint-48_POPE_score.csv @@ -0,0 +1,5 @@ +"split","Overall","acc","precision","recall" +"Overall","87.25099601593625","87.83269961977186","90.87136929460581","83.9080459770115" +"popular","87.4251497005988","88.06818181818183","91.25","83.9080459770115" +"adversarial","84.39306358381502","84.57142857142857","84.88372093023256","83.9080459770115" +"random","90.12345679012346","90.85714285714286","97.33333333333334","83.9080459770115" diff --git a/baseline/checkpoint-48_RealWorldQA.xlsx b/baseline/checkpoint-48_RealWorldQA.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..0656f59874211ba86423688d485e85cd2c8dda5a Binary files /dev/null and b/baseline/checkpoint-48_RealWorldQA.xlsx differ diff --git a/baseline/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl b/baseline/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..afd3c29ad43adcaa6284815dc93f48a2d03f2f30 --- /dev/null +++ b/baseline/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37b36bab627c2045b2635b67f76e001ccaf5cb24ed528d582802d31f9e9022fa +size 17977 diff --git a/baseline/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx b/baseline/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..bd2b1194f15c96ed129850d0ad5863e320610f46 Binary files /dev/null and b/baseline/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx differ diff --git a/baseline/checkpoint-48_RealWorldQA_acc.csv b/baseline/checkpoint-48_RealWorldQA_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..63ba1871046070a38b511ee5c3e05eb5bdbc1598 --- /dev/null +++ b/baseline/checkpoint-48_RealWorldQA_acc.csv @@ -0,0 +1,2 @@ +"split","Overall" +"none","0.7266666666666667" diff --git a/baseline/checkpoint-48_SEEDBench_IMG.xlsx b/baseline/checkpoint-48_SEEDBench_IMG.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..7c678a966871b96ac1912964e3cf4a2b56345613 Binary files /dev/null and b/baseline/checkpoint-48_SEEDBench_IMG.xlsx differ diff --git a/baseline/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl b/baseline/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..79e2a9af3bfa70215e6fb110223d9c16515ec790 --- /dev/null +++ b/baseline/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b9bbfb7dd6744c1930078c6b184e16908630bdf866722c023c3935642f9320 +size 17154 diff --git a/baseline/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx b/baseline/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..25af5a09fe05246ef271f64b513fd74f9ff13431 Binary files /dev/null and b/baseline/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx differ diff --git a/baseline/checkpoint-48_SEEDBench_IMG_acc.csv b/baseline/checkpoint-48_SEEDBench_IMG_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..c0b09a0914d53d2e6f5545da18b4e6683393fb72 --- /dev/null +++ b/baseline/checkpoint-48_SEEDBench_IMG_acc.csv @@ -0,0 +1,2 @@ +"split","Overall","Instance Attributes","Instance Identity","Instance Interaction","Instance Location","Instances Counting","Scene Understanding","Spatial Relation","Text Understanding","Visual Reasoning" +"none","0.7533333333333333","0.8041237113402062","0.8269230769230769","1.0","0.6818181818181818","0.7142857142857143","0.7169811320754716","0.42857142857142855","1.0","0.5" diff --git a/baseline/config.json b/baseline/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d69d8df225fac8280afdc38c657b817439342a47 --- /dev/null +++ b/baseline/config.json @@ -0,0 +1,106 @@ +{ + "architectures": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_size": 3584, + "image_token_id": 151655, + "model_type": "qwen2_5_vl", + "pad_token_id": 151643, + "text_config": { + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 128000, + "max_window_layers": 28, + "model_type": "qwen2_5_vl_text", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_section": [ + 16, + 24, + 24 + ], + "rope_theta": 1000000.0, + "rope_type": "default", + "type": "mrope" + }, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 + }, + "tie_word_embeddings": false, + "transformers_version": "5.3.0", + "use_cache": false, + "video_token_id": 151656, + "vision_config": { + "depth": 32, + "dtype": "bfloat16", + "fullatt_block_indexes": [ + 7, + 15, + 23, + 31 + ], + "hidden_act": "silu", + "hidden_size": 1280, + "in_channels": 3, + "in_chans": 3, + "initializer_range": 0.02, + "intermediate_size": 3420, + "model_type": "qwen2_5_vl", + "num_heads": 16, + "out_hidden_size": 3584, + "patch_size": 14, + "spatial_merge_size": 2, + "spatial_patch_size": 14, + "temporal_patch_size": 2, + "tokens_per_second": 2, + "window_size": 112 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652, + "vision_token_id": 151654 +} diff --git a/baseline/generation_config.json b/baseline/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..02d10ad915167bd3c6a69cdbd79f7e1b27e9d103 --- /dev/null +++ b/baseline/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 1e-06, + "transformers_version": "5.3.0" +} diff --git a/baseline/global_step48/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/baseline/global_step48/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..feb8def9ec1d415a11587a1ec34de8c23ac57b0e --- /dev/null +++ b/baseline/global_step48/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ed248c3b4e8c9c801e7adf60c403bec670701c829cde3a887d2032cd0d1a8fa +size 11423432908 diff --git a/baseline/global_step48/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/baseline/global_step48/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f5469a3f3e589657cfbb7f3ab2b03b23d15ac25 --- /dev/null +++ b/baseline/global_step48/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049b89c3e4b06b933d410577f524d70dbbe788564fc0b1ce27727d4ca0df6e55 +size 11423434124 diff --git a/baseline/global_step48/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/baseline/global_step48/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e3fe78ff3c3476f62f9d813845c982de699d8bc --- /dev/null +++ b/baseline/global_step48/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c017d0fcb640de6051396ad5ea74024771108ffa0c26189c03d3896237cc20cc +size 11423434188 diff --git a/baseline/global_step48/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/baseline/global_step48/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d156e6078093285d252c79143d264caf0a665381 --- /dev/null +++ b/baseline/global_step48/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:740a430b2583b4faa2626bef437ec81603d4d73e68634a815428c1a3adb2532b +size 11423434188 diff --git a/baseline/global_step48/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/baseline/global_step48/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17b965377cc35a56ecfe9ab9fa5631b1a3727eaa --- /dev/null +++ b/baseline/global_step48/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e087173faf1754d7657290eb4d0852fbe35d32649f8bb1674771c26a01e4fadf +size 11423434508 diff --git a/baseline/global_step48/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/baseline/global_step48/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..15d38859bf0158f183009a019f4fffa131f46fbe --- /dev/null +++ b/baseline/global_step48/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5cc877a7dc4afd8f0c036197d77c2208fa2a5140ea27e8d8df50c5443bda503 +size 11423434252 diff --git a/baseline/global_step48/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/baseline/global_step48/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7237ca5d448dd865d9438c3ff1fd03f15508c04f --- /dev/null +++ b/baseline/global_step48/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:685970133249d0320b34ec3d7de201a7af01eb313edb0b56254b3304aca1251d +size 11423434316 diff --git a/baseline/global_step48/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/baseline/global_step48/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..674ed8dd2a9567eebe7755529c97cb5d5f535ac4 --- /dev/null +++ b/baseline/global_step48/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e52c7820a61515f831eeaac03ed5d022174c3cd660ab5f228cfec81225f37213 +size 11423432332 diff --git a/baseline/global_step48/mp_rank_00_model_states.pt b/baseline/global_step48/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..93f4aecb949432bfed53b63d9149bb4e9560f3da --- /dev/null +++ b/baseline/global_step48/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c25d417ce47e3288d42f20b8739ffdb62e3353972dde480826695d5ac4e3c21 +size 16584598266 diff --git a/baseline/latest b/baseline/latest new file mode 100644 index 0000000000000000000000000000000000000000..32b61bf48e124ca282ba181c375b3ab4423b774d --- /dev/null +++ b/baseline/latest @@ -0,0 +1 @@ +global_step48 \ No newline at end of file diff --git a/baseline/model-00001-of-00004.safetensors b/baseline/model-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5719bb9dbd584d4daec0beec0aac3e78d717df1d --- /dev/null +++ b/baseline/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c057f717820ade4177d809a1fc22e6e21feb63b47b548e5c4616bcde25692c01 +size 4976698728 diff --git a/baseline/model-00002-of-00004.safetensors b/baseline/model-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c885cc95a1600243b9883c17216296e8318a9e75 --- /dev/null +++ b/baseline/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64b2e62b421222afa5f276e1b57903400430db0d85e7cff26b98a4cee4e5e0cd +size 4932750984 diff --git a/baseline/model-00003-of-00004.safetensors b/baseline/model-00003-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..398a2c1d736cda8a640994a9e9d4950b7e203dde --- /dev/null +++ b/baseline/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8889463d3bf98c799693f0d7984ff6cc5229cdbd03139bdfcdaa45fb122c3bfc +size 4991495880 diff --git a/baseline/model-00004-of-00004.safetensors b/baseline/model-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f65dc7bb35ed9c1027bb8e89a9d0f066fa5422cd --- /dev/null +++ b/baseline/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c26403d9e5c302fab069fd67bb48b395e23bf93a1c1591c33cf28c6c6f750868 +size 1683468520 diff --git a/baseline/model.safetensors.index.json b/baseline/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..bd9e4e69e006586072470fe13428836fb86741dd --- /dev/null +++ b/baseline/model.safetensors.index.json @@ -0,0 +1,737 @@ +{ + "metadata": { + "total_parameters": 8292166656, + "total_size": 16584333312 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors", + "visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.0.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.0.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.0.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.1.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.1.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.1.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.10.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.10.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.10.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.10.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.10.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.10.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.11.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.11.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.11.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.11.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.11.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.11.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.12.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.12.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.12.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.12.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.12.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.12.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.13.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.13.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.13.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.13.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.13.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.14.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.14.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.14.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.14.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.14.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.14.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.15.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.15.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.15.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.15.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.15.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.15.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.16.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.16.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.16.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.16.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.16.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.16.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.17.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.17.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.17.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.17.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.17.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.18.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.18.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.18.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.18.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.18.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.19.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.19.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.19.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.19.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.19.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.2.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.2.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.2.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.2.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.20.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.20.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.20.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.20.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.20.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.21.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.21.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.21.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.21.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.21.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.22.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.22.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.22.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.23.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.23.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.23.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.24.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.24.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.24.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.25.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.25.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.25.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.26.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.26.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.26.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.27.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.27.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.27.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.27.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.27.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.27.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.27.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.27.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.27.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.28.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.28.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.28.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.28.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.28.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.28.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.28.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.28.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.28.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.29.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.29.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.29.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.29.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.29.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.29.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.29.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.29.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.29.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.3.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.3.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.3.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.30.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.30.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.30.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.30.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.30.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.30.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.30.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.30.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.30.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.31.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.31.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.31.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.31.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.31.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.31.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.31.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.31.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.31.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.4.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.4.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.4.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.4.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.4.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.4.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.5.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.5.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.5.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.5.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.5.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.5.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.6.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.6.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.6.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.6.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.7.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.7.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.7.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.8.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.8.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.8.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.9.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.9.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.9.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors", + "visual.merger.ln_q.weight": "model-00004-of-00004.safetensors", + "visual.merger.mlp.0.bias": "model-00004-of-00004.safetensors", + "visual.merger.mlp.0.weight": "model-00004-of-00004.safetensors", + "visual.merger.mlp.2.bias": "model-00004-of-00004.safetensors", + "visual.merger.mlp.2.weight": "model-00004-of-00004.safetensors", + "visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/baseline/preprocessor_config.json b/baseline/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..7f3b746825e5eef53ed8ed57a91df9e86ee62c0a --- /dev/null +++ b/baseline/preprocessor_config.json @@ -0,0 +1,19 @@ +{ + "min_pixels": 3136, + "max_pixels": 12845056, + "patch_size": 14, + "temporal_patch_size": 2, + "merge_size": 2, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "processor_class": "Qwen2_5_VLProcessor" +} \ No newline at end of file diff --git a/baseline/processor_config.json b/baseline/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9e717d9bf475c411369034636e82e48cf79108a8 --- /dev/null +++ b/baseline/processor_config.json @@ -0,0 +1,63 @@ +{ + "image_processor": { + "data_format": "channels_first", + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "merge_size": 2, + "patch_size": 14, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 12845056, + "shortest_edge": 3136 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen2_5_VLProcessor", + "video_processor": { + "data_format": "channels_first", + "default_to_square": true, + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": false, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "patch_size": 14, + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 12845056, + "shortest_edge": 3136 + }, + "temporal_patch_size": 2, + "video_processor_type": "Qwen2VLVideoProcessor" + } +} diff --git a/baseline/rng_state_0.pth b/baseline/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..70bb784b0c58ed0b3eb0cddf6fc056cb08a72bed --- /dev/null +++ b/baseline/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74386f26f36ed67f56395205881e5db2d0c28ffcbeed50dd95b28771d2dac588 +size 15984 diff --git a/baseline/rng_state_1.pth b/baseline/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..2499ba45f3fa3c8fae84684317e6b4aee7f149aa --- /dev/null +++ b/baseline/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41c88f9de084200454883a13c3717941ea3fd433e2f8735507fc30611f9c5501 +size 15984 diff --git a/baseline/rng_state_2.pth b/baseline/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..add137d3f33cf87f47e15a88fbaa0de654c9edd3 --- /dev/null +++ b/baseline/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965b00d4cb4710ebab57c8787b9925bb3f77b8eeba94a186ec4bc1c2f326ef3f +size 15984 diff --git a/baseline/rng_state_3.pth b/baseline/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..bef02057742082c603c8d9f8a4461cc681973ea4 --- /dev/null +++ b/baseline/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5dc374b8b9a4c45c950f9d136feab85a767081fa59f0c7d68ed3a62060c4949 +size 15984 diff --git a/baseline/rng_state_4.pth b/baseline/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..286cb5eee179bd0d4c28c9f3dfa37722fd466de2 --- /dev/null +++ b/baseline/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c7c212fb779217f1edac0baf44f67b608eefc1e0e4e3f5a9dd7eb557032c1bc +size 15984 diff --git a/baseline/rng_state_5.pth b/baseline/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..90e2da4971b8d28311ac0b2cd1ff750b45e21097 --- /dev/null +++ b/baseline/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86e1effd626ce1e95dd68a0c8089fe19218f2b24dfe9e45ed2cab1c0ebc10ba1 +size 15984 diff --git a/baseline/rng_state_6.pth b/baseline/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..31182d6bb5af342f5e31e07e3e25c961d3f5003b --- /dev/null +++ b/baseline/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:799cc83f60dfc1c4243cfd6403592112414a2eec494e6832f10221c96ff62c20 +size 15984 diff --git a/baseline/rng_state_7.pth b/baseline/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..e9901fae5cb3922ba6a6dc2c5857ecb56e4a434f --- /dev/null +++ b/baseline/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586777c398770c3255d3a1f48c7fef44ea9d89117c627c9ea490e16bfd9a49ba +size 15984 diff --git a/baseline/scheduler.pt b/baseline/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..be6c8aae0e741a986d4254ed90c24030bc3a0975 --- /dev/null +++ b/baseline/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39788f5c12e60a3abb9757db4a3ac31b72797ca865bcb95bcdb8880929fce9a4 +size 1064 diff --git a/baseline/tokenizer.json b/baseline/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..34510ff0037cd50428af467a17ead5a96140a32c --- /dev/null +++ b/baseline/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/baseline/tokenizer_config.json b/baseline/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a32ee6b01c7145a5b88d42f6c19a4b6ff7f682d7 --- /dev/null +++ b/baseline/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": true, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen2_5_VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/baseline/trainer_state.json b/baseline/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..3b68c4081ccdc8ac17314be410a96ac922661dad --- /dev/null +++ b/baseline/trainer_state.json @@ -0,0 +1,114 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 48, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.06477732793522267, + "grad_norm": 2.6904048919677734, + "learning_rate": 3.333333333333333e-07, + "loss": 0.7875139713287354, + "step": 1, + "token_acc": 0.7841123294890244 + }, + { + "epoch": 0.32388663967611336, + "grad_norm": 2.6191625595092773, + "learning_rate": 9.95134034370785e-07, + "loss": 0.7787209749221802, + "step": 5, + "token_acc": 0.7859186270144402 + }, + { + "epoch": 0.6477732793522267, + "grad_norm": 2.2350027561187744, + "learning_rate": 9.414737964294634e-07, + "loss": 0.7690708637237549, + "step": 10, + "token_acc": 0.7875346756409188 + }, + { + "epoch": 0.97165991902834, + "grad_norm": 1.7701807022094727, + "learning_rate": 8.34565303179429e-07, + "loss": 0.7466525554656982, + "step": 15, + "token_acc": 0.7900878692322302 + }, + { + "epoch": 1.2591093117408907, + "grad_norm": 1.4035495519638062, + "learning_rate": 6.87303296707956e-07, + "loss": 0.7205144882202148, + "step": 20, + "token_acc": 0.7961060457644802 + }, + { + "epoch": 1.582995951417004, + "grad_norm": 1.2812139987945557, + "learning_rate": 5.174497483512505e-07, + "loss": 0.6808315277099609, + "step": 25, + "token_acc": 0.8017477767899973 + }, + { + "epoch": 1.9068825910931175, + "grad_norm": 1.1584919691085815, + "learning_rate": 3.454915028125263e-07, + "loss": 0.680242919921875, + "step": 30, + "token_acc": 0.8010927420223759 + }, + { + "epoch": 2.194331983805668, + "grad_norm": 0.9851439595222473, + "learning_rate": 1.9216926233717084e-07, + "loss": 0.6618224143981933, + "step": 35, + "token_acc": 0.8085923445672631 + }, + { + "epoch": 2.5182186234817814, + "grad_norm": 0.9299372434616089, + "learning_rate": 7.597595192178702e-08, + "loss": 0.662947416305542, + "step": 40, + "token_acc": 0.8051387469024985 + }, + { + "epoch": 2.8421052631578947, + "grad_norm": 0.9523605108261108, + "learning_rate": 1.0926199633097154e-08, + "loss": 0.6646108627319336, + "step": 45, + "token_acc": 0.8049214857101155 + } + ], + "logging_steps": 5, + "max_steps": 48, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 5.667590557631775e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/baseline/training_args.bin b/baseline/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..b28607b8025f693fbbe374ce1d4de98b3c9bb582 --- /dev/null +++ b/baseline/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47502853ee42df48e7a989855e2769df19b267ded80a6ed324522c7501b34ad +size 8312 diff --git a/baseline/zero_to_fp32.py b/baseline/zero_to_fp32.py new file mode 100644 index 0000000000000000000000000000000000000000..e69ecd9acb5a235ffbf927091051106d902b3d39 --- /dev/null +++ b/baseline/zero_to_fp32.py @@ -0,0 +1,674 @@ +#!/usr/bin/env python + +# Copyright (c) Microsoft Corporation. +# SPDX-License-Identifier: Apache-2.0 + +# DeepSpeed Team + +# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets +# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in +# the future. Once extracted, the weights don't require DeepSpeed and can be used in any +# application. +# +# example: +# python zero_to_fp32.py . output_dir/ +# or +# python zero_to_fp32.py . output_dir/ --safe_serialization + +import argparse +import torch +import glob +import math +import os +import re +import json +from tqdm import tqdm +from collections import OrderedDict +from dataclasses import dataclass + +# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with +# DeepSpeed data structures it has to be available in the current python environment. +from deepspeed.utils import logger +from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS, + FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES, + FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS) + + +@dataclass +class zero_model_state: + buffers: dict() + param_shapes: dict() + shared_params: list + ds_version: int + frozen_param_shapes: dict() + frozen_param_fragments: dict() + + +debug = 0 + +# load to cpu +device = torch.device('cpu') + + +def atoi(text): + return int(text) if text.isdigit() else text + + +def natural_keys(text): + ''' + alist.sort(key=natural_keys) sorts in human order + http://nedbatchelder.com/blog/200712/human_sorting.html + (See Toothy's implementation in the comments) + ''' + return [atoi(c) for c in re.split(r'(\d+)', text)] + + +def get_model_state_file(checkpoint_dir, zero_stage): + if not os.path.isdir(checkpoint_dir): + raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist") + + # there should be only one file + if zero_stage <= 2: + file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt") + elif zero_stage == 3: + file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt") + + if not os.path.exists(file): + raise FileNotFoundError(f"can't find model states file at '{file}'") + + return file + + +def get_checkpoint_files(checkpoint_dir, glob_pattern): + # XXX: need to test that this simple glob rule works for multi-node setup too + ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys) + + if len(ckpt_files) == 0: + raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'") + + return ckpt_files + + +def get_optim_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt") + + +def get_model_state_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_model_states.pt") + + +def parse_model_states(files): + zero_model_states = [] + for file in files: + state_dict = torch.load(file, map_location=device) + + if BUFFER_NAMES not in state_dict: + raise ValueError(f"{file} is not a model state checkpoint") + buffer_names = state_dict[BUFFER_NAMES] + if debug: + print("Found buffers:", buffer_names) + + # recover just the buffers while restoring them to fp32 if they were saved in fp16 + buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names} + param_shapes = state_dict[PARAM_SHAPES] + + # collect parameters that are included in param_shapes + param_names = [] + for s in param_shapes: + for name in s.keys(): + param_names.append(name) + + # update with frozen parameters + frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None) + if frozen_param_shapes is not None: + if debug: + print(f"Found frozen_param_shapes: {frozen_param_shapes}") + param_names += list(frozen_param_shapes.keys()) + + # handle shared params + shared_params = [[k, v] for k, v in state_dict["shared_params"].items()] + + ds_version = state_dict.get(DS_VERSION, None) + + frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None) + + z_model_state = zero_model_state(buffers=buffers, + param_shapes=param_shapes, + shared_params=shared_params, + ds_version=ds_version, + frozen_param_shapes=frozen_param_shapes, + frozen_param_fragments=frozen_param_fragments) + zero_model_states.append(z_model_state) + + return zero_model_states + + +def parse_optim_states(files, ds_checkpoint_dir): + total_files = len(files) + state_dicts = [] + for f in files: + state_dict = torch.load(f, map_location=device) + # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights + # and also handle the case where it was already removed by another helper script + state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None) + state_dicts.append(state_dict) + + if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]: + raise ValueError(f"{files[0]} is not a zero checkpoint") + zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE] + world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT] + + # For ZeRO-2 each param group can have different partition_count as data parallelism for expert + # parameters can be different from data parallelism for non-expert parameters. So we can just + # use the max of the partition_count to get the dp world_size. + + if type(world_size) is list: + world_size = max(world_size) + + if world_size != total_files: + raise ValueError( + f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. " + "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes." + ) + + # the groups are named differently in each stage + if zero_stage <= 2: + fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS + elif zero_stage == 3: + fp32_groups_key = FP32_FLAT_GROUPS + else: + raise ValueError(f"unknown zero stage {zero_stage}") + + if zero_stage <= 2: + fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))] + elif zero_stage == 3: + # if there is more than one param group, there will be multiple flattened tensors - one + # flattened tensor per group - for simplicity merge them into a single tensor + # + # XXX: could make the script more memory efficient for when there are multiple groups - it + # will require matching the sub-lists of param_shapes for each param group flattened tensor + + fp32_flat_groups = [ + torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts)) + ] + + return zero_stage, world_size, fp32_flat_groups + + +def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters): + """ + Returns fp32 state_dict reconstructed from ds checkpoint + + Args: + - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are) + + """ + print(f"Processing zero checkpoint '{ds_checkpoint_dir}'") + + optim_files = get_optim_files(ds_checkpoint_dir) + zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir) + print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}") + + model_files = get_model_state_files(ds_checkpoint_dir) + + zero_model_states = parse_model_states(model_files) + print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}') + + if zero_stage <= 2: + return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + + +def _zero2_merge_frozen_params(state_dict, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + frozen_param_fragments = zero_model_states[0].frozen_param_fragments + + if debug: + num_elem = sum(s.numel() for s in frozen_param_shapes.values()) + print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in frozen_param_fragments.values()]) + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + state_dict[name] = frozen_param_fragments[name] + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _has_callable(obj, fn): + attr = getattr(obj, fn, None) + return callable(attr) + + +def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + + # Reconstruction protocol: + # + # XXX: document this + + if debug: + for i in range(world_size): + for j in range(len(fp32_flat_groups[0])): + print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}") + + # XXX: memory usage doubles here (zero2) + num_param_groups = len(fp32_flat_groups[0]) + merged_single_partition_of_fp32_groups = [] + for i in range(num_param_groups): + merged_partitions = [sd[i] for sd in fp32_flat_groups] + full_single_fp32_vector = torch.cat(merged_partitions, 0) + merged_single_partition_of_fp32_groups.append(full_single_fp32_vector) + avail_numel = sum( + [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups]) + + if debug: + wanted_params = sum([len(shapes) for shapes in param_shapes]) + wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes]) + # not asserting if there is a mismatch due to possible padding + print(f"Have {avail_numel} numels to process.") + print(f"Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + total_numel = 0 + total_params = 0 + for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups): + offset = 0 + avail_numel = full_single_fp32_vector.numel() + for name, shape in shapes.items(): + + unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape) + total_numel += unpartitioned_numel + total_params += 1 + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape) + offset += unpartitioned_numel + + # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and + # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex + # paddings performed in the code it's almost impossible to predict the exact numbers w/o the + # live optimizer object, so we are checking that the numbers are within the right range + align_to = 2 * world_size + + def zero2_align(x): + return align_to * math.ceil(x / align_to) + + if debug: + print(f"original offset={offset}, avail_numel={avail_numel}") + + offset = zero2_align(offset) + avail_numel = zero2_align(avail_numel) + + if debug: + print(f"aligned offset={offset}, avail_numel={avail_numel}") + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero2_merge_frozen_params(state_dict, zero_model_states) + + _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def zero3_partitioned_param_info(unpartitioned_numel, world_size): + remainder = unpartitioned_numel % world_size + padding_numel = (world_size - remainder) if remainder else 0 + partitioned_numel = math.ceil(unpartitioned_numel / world_size) + return partitioned_numel, padding_numel + + +def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + if debug: + for i in range(world_size): + num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values()) + print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in zero_model_states[0].frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states) + state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape) + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + avail_numel = fp32_flat_groups[0].numel() * world_size + # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each + # param, re-consolidating each param, while dealing with padding if any + + # merge list of dicts, preserving order + param_shapes = {k: v for d in param_shapes for k, v in d.items()} + + if debug: + for i in range(world_size): + print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}") + + wanted_params = len(param_shapes) + wanted_numel = sum(shape.numel() for shape in param_shapes.values()) + # not asserting if there is a mismatch due to possible padding + avail_numel = fp32_flat_groups[0].numel() * world_size + print(f"Trainable params: Have {avail_numel} numels to process.") + print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + offset = 0 + total_numel = 0 + total_params = 0 + for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'): + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + total_params += 1 + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + # XXX: memory usage doubles here + state_dict[name] = torch.cat( + tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)), + 0).narrow(0, 0, unpartitioned_numel).view(shape) + offset += partitioned_numel + + offset *= world_size + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero3_merge_frozen_params(state_dict, world_size, zero_model_states) + + _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with + ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example + via a model hub. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + + Returns: + - pytorch ``state_dict`` + + Note: this approach may not work if your application doesn't have sufficient free CPU memory and + you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with + the checkpoint. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + # do the training and checkpoint saving + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu + model = model.cpu() # move to cpu + model.load_state_dict(state_dict) + # submit to model hub or save the model to share with others + + In this example the ``model`` will no longer be usable in the deepspeed context of the same + application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead. + + """ + if tag is None: + latest_path = os.path.join(checkpoint_dir, 'latest') + if os.path.isfile(latest_path): + with open(latest_path, 'r') as fd: + tag = fd.read().strip() + else: + raise ValueError(f"Unable to find 'latest' file at {latest_path}") + + ds_checkpoint_dir = os.path.join(checkpoint_dir, tag) + + if not os.path.isdir(ds_checkpoint_dir): + raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist") + + return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, + output_dir, + max_shard_size="5GB", + safe_serialization=False, + tag=None, + exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be + loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``output_dir``: directory to the pytorch fp32 state_dict output files + - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB + - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`). + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + """ + # Dependency pre-check + if safe_serialization: + try: + from safetensors.torch import save_file + except ImportError: + print('If you want to use `safe_serialization`, please `pip install safetensors`') + raise + if max_shard_size is not None: + try: + from huggingface_hub import split_torch_state_dict_into_shards + except ImportError: + print('If you want to use `max_shard_size`, please `pip install huggingface_hub`') + raise + + # Convert zero checkpoint to state_dict + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters) + + # Shard the model if it is too big. + weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin" + if max_shard_size is not None: + filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors") + state_dict_split = split_torch_state_dict_into_shards(state_dict, + filename_pattern=filename_pattern, + max_shard_size=max_shard_size) + else: + from collections import namedtuple + StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"]) + state_dict_split = StateDictSplit(is_sharded=False, + filename_to_tensors={weights_name: list(state_dict.keys())}) + + # Save the model + filename_to_tensors = state_dict_split.filename_to_tensors.items() + for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"): + shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors} + output_path = os.path.join(output_dir, shard_file) + if safe_serialization: + save_file(shard, output_path, metadata={"format": "pt"}) + else: + torch.save(shard, output_path) + + # Save index if sharded + if state_dict_split.is_sharded: + index = { + "metadata": state_dict_split.metadata, + "weight_map": state_dict_split.tensor_to_filename, + } + save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json" + save_index_file = os.path.join(output_dir, save_index_file) + with open(save_index_file, "w", encoding="utf-8") as f: + content = json.dumps(index, indent=2, sort_keys=True) + "\n" + f.write(content) + + +def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None): + """ + 1. Put the provided model to cpu + 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` + 3. Load it into the provided model + + Args: + - ``model``: the model object to update + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + + Returns: + - ``model`: modified model + + Make sure you have plenty of CPU memory available before you call this function. If you don't + have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it + conveniently placed for you in the checkpoint folder. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint + model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir) + # submit to model hub or save the model to share with others + + Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context + of the same application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + """ + logger.info(f"Extracting fp32 weights") + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag) + + logger.info(f"Overwriting model with fp32 weights") + model = model.cpu() + model.load_state_dict(state_dict, strict=False) + + return model + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("checkpoint_dir", + type=str, + help="path to the desired checkpoint folder, e.g., path/checkpoint-12") + parser.add_argument("output_dir", + type=str, + help="directory to the pytorch fp32 state_dict output files" + "(e.g. path/checkpoint-12-output/)") + parser.add_argument( + "--max_shard_size", + type=str, + default="5GB", + help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size" + "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`" + "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances" + "without CPU OOM issues.") + parser.add_argument( + "--safe_serialization", + default=False, + action='store_true', + help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).") + parser.add_argument("-t", + "--tag", + type=str, + default=None, + help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1") + parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters") + parser.add_argument("-d", "--debug", action='store_true', help="enable debug") + args = parser.parse_args() + + debug = args.debug + + convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, + args.output_dir, + max_shard_size=args.max_shard_size, + safe_serialization=args.safe_serialization, + tag=args.tag, + exclude_frozen_parameters=args.exclude_frozen_parameters)