diff --git a/.gitattributes b/.gitattributes index d2d040ac63936d8d1a5767001ad7a834ed98d095..971bd06dab76612f2fe23fb02560e74d9ea0a365 100644 --- a/.gitattributes +++ b/.gitattributes @@ -40,3 +40,8 @@ no123/T20260418_G46902c17/checkpoint-48_MMMU_DEV_VAL_Qwen2.5-VL-72B-Instruct_res no123/T20260418_G46902c17/checkpoint-48_MMStar.xlsx filter=lfs diff=lfs merge=lfs -text no123/T20260418_G46902c17/checkpoint-48_MMStar_Qwen2.5-VL-72B-Instruct_result.xlsx filter=lfs diff=lfs merge=lfs -text no123/tokenizer.json filter=lfs diff=lfs merge=lfs -text +no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL.xlsx filter=lfs diff=lfs merge=lfs -text +no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL_Qwen2.5-VL-72B-Instruct_result.xlsx filter=lfs diff=lfs merge=lfs -text +no23_1round/T20260417_G46902c17/checkpoint-48_MMStar.xlsx filter=lfs diff=lfs merge=lfs -text +no23_1round/T20260417_G46902c17/checkpoint-48_MMStar_Qwen2.5-VL-72B-Instruct_result.xlsx filter=lfs diff=lfs merge=lfs -text +no23_1round/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/no23_1round/T20260406_Ge59eba20/08_MMMU_DEV_VAL.pkl b/no23_1round/T20260406_Ge59eba20/08_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8a079e5bed4cee9d9652eacd418df0f851bd5dbd --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/08_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba7767128d2167924fe961d620be33707c32b3c6d88c9255a769a3694961f83 +size 139106 diff --git a/no23_1round/T20260406_Ge59eba20/18_MMMU_DEV_VAL.pkl b/no23_1round/T20260406_Ge59eba20/18_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..1cba79fe4ddab0a2ffebca57d47ca038e944fa5b --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/18_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315d0073df6316d2a17f19132d19bf2ae4feaa504d184f3ec4a40a30773cf3de +size 147857 diff --git a/no23_1round/T20260406_Ge59eba20/18_VStarBench.pkl b/no23_1round/T20260406_Ge59eba20/18_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c280ac519825794d4058983d91a7da555178afdd --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/18_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a724685d86fa7a025c5c0d9c2d02251061736eb64c307774f583540c9a4fa42 +size 1674 diff --git a/no23_1round/T20260406_Ge59eba20/28_MMMU_DEV_VAL.pkl b/no23_1round/T20260406_Ge59eba20/28_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..5ef2e93c5e95bd090e037becbec5fe093b36718c --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/28_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bbd758a8215b10b88887903e2bb95c057a122391cadfc8144726f9dcd91e1a1 +size 137038 diff --git a/no23_1round/T20260406_Ge59eba20/28_VStarBench.pkl b/no23_1round/T20260406_Ge59eba20/28_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f33a791095edf75f678db272d10b77eaa4da631b --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/28_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fdbbc450092b9f3fe7581d161b31c2b67b76c870cb4081361e346cba31afc5 +size 1672 diff --git a/no23_1round/T20260406_Ge59eba20/38_MMMU_DEV_VAL.pkl b/no23_1round/T20260406_Ge59eba20/38_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..2ccf0fb1152e982d2c8a07d45b42d655ed277b0e --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/38_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f59ea8127830f98b6c3401e02ea7f41171c9b963ac15e0b5d8724f8ef30ec78 +size 35889 diff --git a/no23_1round/T20260406_Ge59eba20/38_VStarBench.pkl b/no23_1round/T20260406_Ge59eba20/38_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9cf2119d57813fc27cf71ed24b7f469b3f559fd2 --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/38_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71387d5f8591c3b4d1a054d1f55b1432da117486f9fb160c9658020735a7dd2a +size 2222 diff --git a/no23_1round/T20260406_Ge59eba20/48_MMMU_DEV_VAL.pkl b/no23_1round/T20260406_Ge59eba20/48_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a8613365facb0125f0bd951fe1b770c4f999b905 --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/48_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c2ebcf341afbc30ede427d5e8bf56b7314638cc99525378e54415fbededa7ac +size 96852 diff --git a/no23_1round/T20260406_Ge59eba20/48_VStarBench.pkl b/no23_1round/T20260406_Ge59eba20/48_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ccb3f75261c3b9168cfbf39f1904649576521be9 --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/48_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28963efd0cea5dcbc6e80cb320ad3c81362c1fa9b7af8019b3029164bf9c1f50 +size 1875 diff --git a/no23_1round/T20260406_Ge59eba20/58_MMMU_DEV_VAL.pkl b/no23_1round/T20260406_Ge59eba20/58_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..32fa9bca3c7d8dce873822f6b80b6c9d67fb2959 --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/58_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38e0b0c9e3739abfee6a6712ef8ed2ee3db55219c37a7e993a874114400eefcf +size 160807 diff --git a/no23_1round/T20260406_Ge59eba20/58_VStarBench.pkl b/no23_1round/T20260406_Ge59eba20/58_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..045ddc3b68c63811d604156910f6c56b2333a0cd --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/58_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1c3f9030ec6ec790e8d3e6248c1bb5ae90b0d3258c772691f5962d53ec77de +size 1023 diff --git a/no23_1round/T20260406_Ge59eba20/68_MMMU_DEV_VAL.pkl b/no23_1round/T20260406_Ge59eba20/68_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ba389ef761916324b2f7d8dca83326c6736ec376 --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/68_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e906122a76550f423fb2220c91221e92bc948fefdead7f9ba483fe08ca990c0 +size 154677 diff --git a/no23_1round/T20260406_Ge59eba20/68_VStarBench.pkl b/no23_1round/T20260406_Ge59eba20/68_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..93673bb05ba0de76db3d8b2f7f007ccf56888c6c --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/68_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb8f08245afbd55d693c7b27bef3498e14c3e81689ad65371f9be1afd1c10fa +size 1680 diff --git a/no23_1round/T20260406_Ge59eba20/78_MMMU_DEV_VAL.pkl b/no23_1round/T20260406_Ge59eba20/78_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..7d9b0f04f139a7d1a0a06500492e396ee1f1da9a --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/78_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c674f905c8db798cd7632ce162d675f5cff64ff524292e549fd7b776b340af +size 158456 diff --git a/no23_1round/T20260406_Ge59eba20/78_VStarBench.pkl b/no23_1round/T20260406_Ge59eba20/78_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..51256cf91434250ffb4624663821590b545f56eb --- /dev/null +++ b/no23_1round/T20260406_Ge59eba20/78_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91983b5dacbac9910ab75271bb9b4c7372cfe330efd1ac2d70e46ee5197e40d +size 1608 diff --git a/no23_1round/T20260412_G598544dc/08_MMMU_DEV_VAL.pkl b/no23_1round/T20260412_G598544dc/08_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..d11d2cbfc23ce2e0255ebbdb7ba4792ee8960bfc --- /dev/null +++ b/no23_1round/T20260412_G598544dc/08_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da334dbda4a86a4ae228b4678102fb00707641968c822ae9c5fc87f60bb0e42 +size 21438 diff --git a/no23_1round/T20260412_G598544dc/18_VStarBench.pkl b/no23_1round/T20260412_G598544dc/18_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c280ac519825794d4058983d91a7da555178afdd --- /dev/null +++ b/no23_1round/T20260412_G598544dc/18_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a724685d86fa7a025c5c0d9c2d02251061736eb64c307774f583540c9a4fa42 +size 1674 diff --git a/no23_1round/T20260412_G598544dc/28_VStarBench.pkl b/no23_1round/T20260412_G598544dc/28_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f33a791095edf75f678db272d10b77eaa4da631b --- /dev/null +++ b/no23_1round/T20260412_G598544dc/28_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fdbbc450092b9f3fe7581d161b31c2b67b76c870cb4081361e346cba31afc5 +size 1672 diff --git a/no23_1round/T20260412_G598544dc/38_VStarBench.pkl b/no23_1round/T20260412_G598544dc/38_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9cf2119d57813fc27cf71ed24b7f469b3f559fd2 --- /dev/null +++ b/no23_1round/T20260412_G598544dc/38_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71387d5f8591c3b4d1a054d1f55b1432da117486f9fb160c9658020735a7dd2a +size 2222 diff --git a/no23_1round/T20260412_G598544dc/48_VStarBench.pkl b/no23_1round/T20260412_G598544dc/48_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ccb3f75261c3b9168cfbf39f1904649576521be9 --- /dev/null +++ b/no23_1round/T20260412_G598544dc/48_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28963efd0cea5dcbc6e80cb320ad3c81362c1fa9b7af8019b3029164bf9c1f50 +size 1875 diff --git a/no23_1round/T20260412_G598544dc/58_VStarBench.pkl b/no23_1round/T20260412_G598544dc/58_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..045ddc3b68c63811d604156910f6c56b2333a0cd --- /dev/null +++ b/no23_1round/T20260412_G598544dc/58_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1c3f9030ec6ec790e8d3e6248c1bb5ae90b0d3258c772691f5962d53ec77de +size 1023 diff --git a/no23_1round/T20260412_G598544dc/68_VStarBench.pkl b/no23_1round/T20260412_G598544dc/68_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..93673bb05ba0de76db3d8b2f7f007ccf56888c6c --- /dev/null +++ b/no23_1round/T20260412_G598544dc/68_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb8f08245afbd55d693c7b27bef3498e14c3e81689ad65371f9be1afd1c10fa +size 1680 diff --git a/no23_1round/T20260412_G598544dc/78_VStarBench.pkl b/no23_1round/T20260412_G598544dc/78_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..51256cf91434250ffb4624663821590b545f56eb --- /dev/null +++ b/no23_1round/T20260412_G598544dc/78_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91983b5dacbac9910ab75271bb9b4c7372cfe330efd1ac2d70e46ee5197e40d +size 1608 diff --git a/no23_1round/T20260413_G598544dc/08_MMMU_DEV_VAL.pkl b/no23_1round/T20260413_G598544dc/08_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..d11d2cbfc23ce2e0255ebbdb7ba4792ee8960bfc --- /dev/null +++ b/no23_1round/T20260413_G598544dc/08_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da334dbda4a86a4ae228b4678102fb00707641968c822ae9c5fc87f60bb0e42 +size 21438 diff --git a/no23_1round/T20260413_G598544dc/18_VStarBench.pkl b/no23_1round/T20260413_G598544dc/18_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c280ac519825794d4058983d91a7da555178afdd --- /dev/null +++ b/no23_1round/T20260413_G598544dc/18_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a724685d86fa7a025c5c0d9c2d02251061736eb64c307774f583540c9a4fa42 +size 1674 diff --git a/no23_1round/T20260413_G598544dc/28_VStarBench.pkl b/no23_1round/T20260413_G598544dc/28_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f33a791095edf75f678db272d10b77eaa4da631b --- /dev/null +++ b/no23_1round/T20260413_G598544dc/28_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fdbbc450092b9f3fe7581d161b31c2b67b76c870cb4081361e346cba31afc5 +size 1672 diff --git a/no23_1round/T20260413_G598544dc/38_VStarBench.pkl b/no23_1round/T20260413_G598544dc/38_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9cf2119d57813fc27cf71ed24b7f469b3f559fd2 --- /dev/null +++ b/no23_1round/T20260413_G598544dc/38_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71387d5f8591c3b4d1a054d1f55b1432da117486f9fb160c9658020735a7dd2a +size 2222 diff --git a/no23_1round/T20260413_G598544dc/48_VStarBench.pkl b/no23_1round/T20260413_G598544dc/48_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ccb3f75261c3b9168cfbf39f1904649576521be9 --- /dev/null +++ b/no23_1round/T20260413_G598544dc/48_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28963efd0cea5dcbc6e80cb320ad3c81362c1fa9b7af8019b3029164bf9c1f50 +size 1875 diff --git a/no23_1round/T20260413_G598544dc/58_VStarBench.pkl b/no23_1round/T20260413_G598544dc/58_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..045ddc3b68c63811d604156910f6c56b2333a0cd --- /dev/null +++ b/no23_1round/T20260413_G598544dc/58_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1c3f9030ec6ec790e8d3e6248c1bb5ae90b0d3258c772691f5962d53ec77de +size 1023 diff --git a/no23_1round/T20260413_G598544dc/68_VStarBench.pkl b/no23_1round/T20260413_G598544dc/68_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..93673bb05ba0de76db3d8b2f7f007ccf56888c6c --- /dev/null +++ b/no23_1round/T20260413_G598544dc/68_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb8f08245afbd55d693c7b27bef3498e14c3e81689ad65371f9be1afd1c10fa +size 1680 diff --git a/no23_1round/T20260413_G598544dc/78_VStarBench.pkl b/no23_1round/T20260413_G598544dc/78_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..51256cf91434250ffb4624663821590b545f56eb --- /dev/null +++ b/no23_1round/T20260413_G598544dc/78_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91983b5dacbac9910ab75271bb9b4c7372cfe330efd1ac2d70e46ee5197e40d +size 1608 diff --git a/no23_1round/T20260417_G46902c17/04_MMStar.pkl b/no23_1round/T20260417_G46902c17/04_MMStar.pkl new file mode 100644 index 0000000000000000000000000000000000000000..4099cb4a7331b75ede8a0aabe0ab4d3054ae33b7 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/04_MMStar.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb1a5cd6fe9df8960aaf4de52fd24a1526508b196a746e55b15f1af2d18ef2cc +size 7229 diff --git a/no23_1round/T20260417_G46902c17/08_HRBench4K.pkl b/no23_1round/T20260417_G46902c17/08_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..1bd7db5aa9c5dc56529e835333d5710ab93ef684 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/08_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ca214bf645763cf0c997322f940c6d0bce15d2de1820a348cd22de99bffac5 +size 2211 diff --git a/no23_1round/T20260417_G46902c17/08_MMMU_DEV_VAL.pkl b/no23_1round/T20260417_G46902c17/08_MMMU_DEV_VAL.pkl new file mode 100644 index 0000000000000000000000000000000000000000..0abbe30d04d6a1d4a6b1f22cf79d1de0a365749f --- /dev/null +++ b/no23_1round/T20260417_G46902c17/08_MMMU_DEV_VAL.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5be469f592281e365cc0fd09d4bc91e527357d2e5ee677549e7d0fa556cb1af +size 23770 diff --git a/no23_1round/T20260417_G46902c17/14_MMStar.pkl b/no23_1round/T20260417_G46902c17/14_MMStar.pkl new file mode 100644 index 0000000000000000000000000000000000000000..5d392b3f7b120d3ca3c24b316eee14f1b18dded5 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/14_MMStar.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04be2d1735b862fc7552a3ff95ff6b87811cc6fdeefde89f92af4ecf94aa27c1 +size 60973 diff --git a/no23_1round/T20260417_G46902c17/18_HRBench4K.pkl b/no23_1round/T20260417_G46902c17/18_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..0fb1e766dbdc143fe96077c8fb31caa02ffafafa --- /dev/null +++ b/no23_1round/T20260417_G46902c17/18_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db2fef65b7f4d74f81a03a934912920e28fef25d7dd53bdda4f48fc0f1f5aff2 +size 4560 diff --git a/no23_1round/T20260417_G46902c17/18_VStarBench.pkl b/no23_1round/T20260417_G46902c17/18_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c280ac519825794d4058983d91a7da555178afdd --- /dev/null +++ b/no23_1round/T20260417_G46902c17/18_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a724685d86fa7a025c5c0d9c2d02251061736eb64c307774f583540c9a4fa42 +size 1674 diff --git a/no23_1round/T20260417_G46902c17/24_MMStar.pkl b/no23_1round/T20260417_G46902c17/24_MMStar.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a13fe5cdd260fe197422455939f8464097c2beee --- /dev/null +++ b/no23_1round/T20260417_G46902c17/24_MMStar.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562f13594876c346878fabb62dc45752a7ecb176ba708f661c865e0680fd4ed8 +size 14022 diff --git a/no23_1round/T20260417_G46902c17/28_HRBench4K.pkl b/no23_1round/T20260417_G46902c17/28_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..0db769606c93661d6b52a0e1c8209827b55ae2b7 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/28_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7aa2c38bea879956559ec47f18ddf676ffaafff640c5b80e4cfe956a216ceb8 +size 2870 diff --git a/no23_1round/T20260417_G46902c17/28_VStarBench.pkl b/no23_1round/T20260417_G46902c17/28_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f33a791095edf75f678db272d10b77eaa4da631b --- /dev/null +++ b/no23_1round/T20260417_G46902c17/28_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fdbbc450092b9f3fe7581d161b31c2b67b76c870cb4081361e346cba31afc5 +size 1672 diff --git a/no23_1round/T20260417_G46902c17/34_MMStar.pkl b/no23_1round/T20260417_G46902c17/34_MMStar.pkl new file mode 100644 index 0000000000000000000000000000000000000000..e50fcd7b019d902863990e8d1295d3d785725400 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/34_MMStar.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3a2bae6f7b3f77c18e09f942864a0ffae712176c7ec70f9a9f9fb7b353f070b +size 93277 diff --git a/no23_1round/T20260417_G46902c17/38_HRBench4K.pkl b/no23_1round/T20260417_G46902c17/38_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..0a6881b1ee35257a7f8f8b4e1cc6e1db17b90f5f --- /dev/null +++ b/no23_1round/T20260417_G46902c17/38_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced67bd8898a6a33ca8d4f27e93a5aa99379ff9b329342fceea30b06bc46b5ff +size 10021 diff --git a/no23_1round/T20260417_G46902c17/38_VStarBench.pkl b/no23_1round/T20260417_G46902c17/38_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9cf2119d57813fc27cf71ed24b7f469b3f559fd2 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/38_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71387d5f8591c3b4d1a054d1f55b1432da117486f9fb160c9658020735a7dd2a +size 2222 diff --git a/no23_1round/T20260417_G46902c17/48_HRBench4K.pkl b/no23_1round/T20260417_G46902c17/48_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..eeecab6f251698e3ffd6d6dc159450a1889a2e21 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/48_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88b9d7b2a0ef253c673d4df50c16d059f9168d8fd26e6a146506c52d76a005b +size 4374 diff --git a/no23_1round/T20260417_G46902c17/48_VStarBench.pkl b/no23_1round/T20260417_G46902c17/48_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ccb3f75261c3b9168cfbf39f1904649576521be9 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/48_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28963efd0cea5dcbc6e80cb320ad3c81362c1fa9b7af8019b3029164bf9c1f50 +size 1875 diff --git a/no23_1round/T20260417_G46902c17/58_HRBench4K.pkl b/no23_1round/T20260417_G46902c17/58_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f66843070bbc73d1e160cbc825dc5a89a7c05f7c --- /dev/null +++ b/no23_1round/T20260417_G46902c17/58_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b57c1c8ccbc8c37bba5a8f66812e771f451528f59137b1b49d63f624839f0163 +size 4573 diff --git a/no23_1round/T20260417_G46902c17/58_VStarBench.pkl b/no23_1round/T20260417_G46902c17/58_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..045ddc3b68c63811d604156910f6c56b2333a0cd --- /dev/null +++ b/no23_1round/T20260417_G46902c17/58_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1c3f9030ec6ec790e8d3e6248c1bb5ae90b0d3258c772691f5962d53ec77de +size 1023 diff --git a/no23_1round/T20260417_G46902c17/68_HRBench4K.pkl b/no23_1round/T20260417_G46902c17/68_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..06fa1cd065677eb4646df3ee1cf93befe99256a4 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/68_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782f30c3bfa5b11a73502407326b5def0c7fdc49c0dc89d1f60820b35f415d64 +size 4199 diff --git a/no23_1round/T20260417_G46902c17/68_VStarBench.pkl b/no23_1round/T20260417_G46902c17/68_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..93673bb05ba0de76db3d8b2f7f007ccf56888c6c --- /dev/null +++ b/no23_1round/T20260417_G46902c17/68_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb8f08245afbd55d693c7b27bef3498e14c3e81689ad65371f9be1afd1c10fa +size 1680 diff --git a/no23_1round/T20260417_G46902c17/78_HRBench4K.pkl b/no23_1round/T20260417_G46902c17/78_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8b59a759a076844516143a0ea267dde5f16bdb23 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/78_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05b564a3f6bd7c8150f163f9d51551f21fc2ccc4ff06481e1f4fc1bc0683b404 +size 4602 diff --git a/no23_1round/T20260417_G46902c17/78_VStarBench.pkl b/no23_1round/T20260417_G46902c17/78_VStarBench.pkl new file mode 100644 index 0000000000000000000000000000000000000000..51256cf91434250ffb4624663821590b545f56eb --- /dev/null +++ b/no23_1round/T20260417_G46902c17/78_VStarBench.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91983b5dacbac9910ab75271bb9b4c7372cfe330efd1ac2d70e46ee5197e40d +size 1608 diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K.xlsx b/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..91671daec023864456ff793c246918b425576cdd Binary files /dev/null and b/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K.xlsx differ diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_PREV.pkl b/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_PREV.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b6efe5b19b4701eeaa416a87bc5d38e72d73ce57 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_PREV.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074bc4174e75a1c33ee96d667ac05e8ce24cb7e76279771f8820c18219e0146f +size 38636 diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_Qwen2.5-VL-72B-Instruct_result.pkl b/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..88acc231e9967887589c150725e3d7aaa977e350 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_Qwen2.5-VL-72B-Instruct_result.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e9e7d4b51c8b012f49fc0b81671bbd3aec2f70bbcbe775dce87ffb7db16e805 +size 43929 diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_Qwen2.5-VL-72B-Instruct_result.xlsx b/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..28fbd17555ce906ec75608731af7af6950a2959b Binary files /dev/null and b/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_Qwen2.5-VL-72B-Instruct_result.xlsx differ diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_acc.csv b/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..6d241426042a9a80506207ab39aa3c030da0373d --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_HRBench8K_acc.csv @@ -0,0 +1,16 @@ +"cycle","type","accuracy" +"0","all","0.665" +"0","single","0.8" +"0","cross","0.53" +"1","all","0.725" +"1","single","0.83" +"1","cross","0.62" +"2","all","0.765" +"2","single","0.86" +"2","cross","0.67" +"3","all","0.68" +"3","single","0.83" +"3","cross","0.53" +"Average","all","0.7087500000000001" +"Average","single","0.83" +"Average","cross","0.5874999999999999" diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL.xlsx b/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..fb0e63dd570247ece1d77fcf4cba3b10901028c4 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL.xlsx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3f59b203a4069cc1ad7240e91133e005a7f8ba1a566e1f05eb1954e6906b691 +size 356014 diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL_Qwen2.5-VL-72B-Instruct_result.pkl b/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..1a6ab242085d46b7a91038189880a62c771824f3 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL_Qwen2.5-VL-72B-Instruct_result.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45dfd11bf87d0147f3f6eff8fb127b75f8abb00397d5600b23981694a55eda40 +size 54045 diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL_Qwen2.5-VL-72B-Instruct_result.xlsx b/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..d780516938cf43bfe67a396593d04eace1e7511f --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL_Qwen2.5-VL-72B-Instruct_result.xlsx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31e0a30cff60d063daab1d713102d31e9dc32c0458d5477b22d7c3b7ad90e35 +size 369340 diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL_acc.csv b/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..183d75a711ae98c50fcce4b33e31e87d50eabe54 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_MMMU_DEV_VAL_acc.csv @@ -0,0 +1,3 @@ +"split","Overall","Accounting","Agriculture","Architecture_and_Engineering","Art","Art_Theory","Basic_Medical_Science","Biology","Chemistry","Clinical_Medicine","Computer_Science","Design","Diagnostics_and_Laboratory_Medicine","Economics","Electronics","Energy_and_Power","Finance","Geography","History","Literature","Manage","Marketing","Materials","Math","Mechanical_Engineering","Music","Pharmacy","Physics","Psychology","Public_Health","Sociology","Art & Design","Business","Health & Medicine","Humanities & Social Science","Science","Tech & Engineering" +"validation","0.48777777777777775","0.4","0.5","0.3","0.6","0.8","0.6333333333333333","0.43333333333333335","0.43333333333333335","0.6333333333333333","0.4","0.7","0.36666666666666664","0.4666666666666667","0.3333333333333333","0.3","0.23333333333333334","0.43333333333333335","0.7333333333333333","0.8333333333333334","0.4","0.5333333333333333","0.26666666666666666","0.4","0.23333333333333334","0.3333333333333333","0.6666666666666666","0.43333333333333335","0.7","0.43333333333333335","0.7","0.6083333333333333","0.4066666666666667","0.5466666666666666","0.7416666666666667","0.4266666666666667","0.3333333333333333" +"dev","0.49333333333333335","0.4","0.2","0.2","0.8","0.8","0.8","0.8","0.6","0.2","0.6","0.8","0.4","0.4","0.2","0.0","0.4","0.0","1.0","0.6","0.6","0.0","0.4","0.6","0.2","0.4","0.8","0.6","0.8","0.4","0.8","0.7","0.36","0.52","0.8","0.52","0.2571428571428571" diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar.xlsx b/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..f4f47e07e69c9ce2b7b9251d9693d54ab5a3c04a --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar.xlsx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d97462844aef0b1b17e0dfbbd55830f48cab12cf3026c897cb2e7fb6fe80d884 +size 181255 diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar_Qwen2.5-VL-72B-Instruct_result.pkl b/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..387dff392767eb1f2815f1be5ed839d16e283455 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar_Qwen2.5-VL-72B-Instruct_result.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7946dea044cb3da7f2b718cc5a9919140612758b14387c68a21f7cb876126139 +size 88000 diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar_Qwen2.5-VL-72B-Instruct_result.xlsx b/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..badb151ce93444c9e3dbf7016139170428c013ea --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar_Qwen2.5-VL-72B-Instruct_result.xlsx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e314e289313c5819bf7318dafeacb9eac02c3681f1c732f8755a0468ca577252 +size 201928 diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar_acc.csv b/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..ca3ec9743bc567bba03ba1cf9de761225eee5ebb --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_MMStar_acc.csv @@ -0,0 +1,2 @@ +"split","Overall","coarse perception","fine-grained perception","instance reasoning","logical reasoning","math","science & technology" +"none","0.6146666666666667","0.684","0.48","0.7","0.7","0.644","0.48" diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_VStarBench.xlsx b/no23_1round/T20260417_G46902c17/checkpoint-48_VStarBench.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..226227657d3cec52645e8cb7b0d42122b86e60c8 Binary files /dev/null and b/no23_1round/T20260417_G46902c17/checkpoint-48_VStarBench.xlsx differ diff --git a/no23_1round/T20260417_G46902c17/checkpoint-48_VStarBench_PREV.pkl b/no23_1round/T20260417_G46902c17/checkpoint-48_VStarBench_PREV.pkl new file mode 100644 index 0000000000000000000000000000000000000000..860b263a54c0f00daec2a0a380aeffb53d832862 --- /dev/null +++ b/no23_1round/T20260417_G46902c17/checkpoint-48_VStarBench_PREV.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8e18079364cc29ac9e0bc42c36cb6d04db6dc5c60ce9888d94ff38c291ee25b +size 10585 diff --git a/no23_1round/T20260418_G46902c17/03_HRBench4K.pkl b/no23_1round/T20260418_G46902c17/03_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c9df686493084f48cd2c51d1fa9a1d5d224c8aa9 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/03_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ead1791f6168876da111e25c3838001b4f6f147723402843c3d3ff6a09e7b86 +size 9009 diff --git a/no23_1round/T20260418_G46902c17/03_MMStar.pkl b/no23_1round/T20260418_G46902c17/03_MMStar.pkl new file mode 100644 index 0000000000000000000000000000000000000000..74769f583c9fb3815ae53cacfc66906d826923a0 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/03_MMStar.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13a6daef07bbc13a408bb2450cb1901956f391c594470ab7f8bba355d1ebb5b1 +size 2025 diff --git a/no23_1round/T20260418_G46902c17/08_HRBench8K.pkl b/no23_1round/T20260418_G46902c17/08_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..316f453d9a38dd717cfdaade352ae267aee0b932 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/08_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38f0f66ebb33e7f3624ff3cdeaec7f288af9bbd3afa4f67c46a34b8d9592b4c7 +size 5956 diff --git a/no23_1round/T20260418_G46902c17/13_HRBench4K.pkl b/no23_1round/T20260418_G46902c17/13_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..921ab25ec5f2cfbd65b12dfb638b34a7fc899641 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/13_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdad45155528ed70067c6bf71523cbf0ca1ccd99c89f376f16c0304b41f92bdb +size 4018 diff --git a/no23_1round/T20260418_G46902c17/13_MMStar.pkl b/no23_1round/T20260418_G46902c17/13_MMStar.pkl new file mode 100644 index 0000000000000000000000000000000000000000..3534a8a65d4db89900bccc3bb16d649ce7c9fe23 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/13_MMStar.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332a70708377261db8d0f7a57afa8ec7cdac9f06774ff14a0f006dd47026e7e3 +size 12074 diff --git a/no23_1round/T20260418_G46902c17/18_HRBench8K.pkl b/no23_1round/T20260418_G46902c17/18_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ffa17371c500cdbdb56487a7cacef1fa4254e28c --- /dev/null +++ b/no23_1round/T20260418_G46902c17/18_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6664e2ce5a3f82cbf812c99bd44aa6487f779a221cbd2d61e3d5a802c851921 +size 10669 diff --git a/no23_1round/T20260418_G46902c17/23_HRBench4K.pkl b/no23_1round/T20260418_G46902c17/23_HRBench4K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c6ab25ac48dbc389a5530a656d1ee1a9acf28457 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/23_HRBench4K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92a96609749cd5790be30adf19e5158fa3d7123e8752fe44c243d76b1602dedb +size 3078 diff --git a/no23_1round/T20260418_G46902c17/23_MMStar.pkl b/no23_1round/T20260418_G46902c17/23_MMStar.pkl new file mode 100644 index 0000000000000000000000000000000000000000..2c642db26d8359341afa7c5613cec9ea429e969e --- /dev/null +++ b/no23_1round/T20260418_G46902c17/23_MMStar.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e1d8375c6d79a269c56037ff4cb7bac8437522cbeb53de9b75eb1648837faf3 +size 2201 diff --git a/no23_1round/T20260418_G46902c17/28_HRBench8K.pkl b/no23_1round/T20260418_G46902c17/28_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..3322e17aeb2ede742ae0d593731853d75d67fa53 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/28_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8f39c422457526238f7af3985145db14890e9e1d8aacb8d6cf44942400567e +size 5998 diff --git a/no23_1round/T20260418_G46902c17/38_HRBench8K.pkl b/no23_1round/T20260418_G46902c17/38_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..1144de695759ecd11ed357530a52957f3ae01ab3 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/38_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0c38c3b3a6aa0c2a2de95df446b31f11e7b49c04387bc171b3f472dba9be9f +size 17980 diff --git a/no23_1round/T20260418_G46902c17/48_HRBench8K.pkl b/no23_1round/T20260418_G46902c17/48_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..76cc2c8fcb62af2ea94726d6e29c8fa5d7bce8d3 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/48_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4411db02b777de658f33a6ec449ffa71988f32ff055f857c3a2e22c0fd7a8fb +size 10179 diff --git a/no23_1round/T20260418_G46902c17/58_HRBench8K.pkl b/no23_1round/T20260418_G46902c17/58_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..199ada62cc71073aea2582623b9a7c3d2314df88 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/58_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a667f6db7b8c2e11a6f475e77baea02e0f2db862dddc7857b330524dfb88bf7 +size 10769 diff --git a/no23_1round/T20260418_G46902c17/68_HRBench8K.pkl b/no23_1round/T20260418_G46902c17/68_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..9a732d9656d22f0da2b2e8c2b439df430b6c9e58 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/68_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:058a172aa0f0ea5f9c2a4e1ab7202cfdc6e67e3f59d195825134a5e923804871 +size 9621 diff --git a/no23_1round/T20260418_G46902c17/78_HRBench8K.pkl b/no23_1round/T20260418_G46902c17/78_HRBench8K.pkl new file mode 100644 index 0000000000000000000000000000000000000000..95acea78360eaab2b6b3c982f4b37b1691e8c13b --- /dev/null +++ b/no23_1round/T20260418_G46902c17/78_HRBench8K.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a53cbf7073768d71ad6fb974659920cb844424abc4b6e55887cce34a00f5938 +size 11774 diff --git a/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K.xlsx b/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..4244d1c08d94fa29ab39b8bda6b43052f149593e Binary files /dev/null and b/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K.xlsx differ diff --git a/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K_Qwen2.5-VL-72B-Instruct_result.pkl b/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..af91bbc4ec13fd512560827a4fc2e31a0271b6c1 --- /dev/null +++ b/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K_Qwen2.5-VL-72B-Instruct_result.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:738df97db01be7aefa0e06ce0d4d068ee5426d77434a7f30c64b46256541b86e +size 69327 diff --git a/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K_Qwen2.5-VL-72B-Instruct_result.xlsx b/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..839601a3753f162be1d1ae9b393f1bcd0bc45bc3 Binary files /dev/null and b/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K_Qwen2.5-VL-72B-Instruct_result.xlsx differ diff --git a/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K_acc.csv b/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..739bf1244ab34490848418f3f3fa0a6917ae15ea --- /dev/null +++ b/no23_1round/T20260418_G46902c17/checkpoint-48_HRBench4K_acc.csv @@ -0,0 +1,16 @@ +"cycle","type","accuracy" +"0","all","0.68" +"0","single","0.85" +"0","cross","0.51" +"1","all","0.67" +"1","single","0.79" +"1","cross","0.55" +"2","all","0.74" +"2","single","0.84" +"2","cross","0.64" +"3","all","0.69" +"3","single","0.8" +"3","cross","0.58" +"Average","all","0.695" +"Average","single","0.8200000000000001" +"Average","cross","0.5700000000000001" diff --git a/no23_1round/T20260423_G2383b931/04_RealWorldQA.pkl b/no23_1round/T20260423_G2383b931/04_RealWorldQA.pkl new file mode 100644 index 0000000000000000000000000000000000000000..62ba55ddb81685d797461a8ec0f9ec6b269fa701 --- /dev/null +++ b/no23_1round/T20260423_G2383b931/04_RealWorldQA.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5543fcd260adc0c7883cfcade34e0d237ecc6cb65e283e39dcb53a67a141fc35 +size 3469 diff --git a/no23_1round/T20260423_G2383b931/14_RealWorldQA.pkl b/no23_1round/T20260423_G2383b931/14_RealWorldQA.pkl new file mode 100644 index 0000000000000000000000000000000000000000..6c6da85b14cf0279b39c7822495336ab68560ddf --- /dev/null +++ b/no23_1round/T20260423_G2383b931/14_RealWorldQA.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be368c7cee5894c3333da64afdc803b58a231a3ef14fb2823c7c14492e7cb96 +size 3463 diff --git a/no23_1round/T20260423_G2383b931/24_RealWorldQA.pkl b/no23_1round/T20260423_G2383b931/24_RealWorldQA.pkl new file mode 100644 index 0000000000000000000000000000000000000000..cc16340aea2d982373cbb3c008d1684018749579 --- /dev/null +++ b/no23_1round/T20260423_G2383b931/24_RealWorldQA.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944780568392d876f8333cc166f855de2fe8c86e8da9f75b2c2373ee4ec31c0d +size 5184 diff --git a/no23_1round/T20260423_G2383b931/34_RealWorldQA.pkl b/no23_1round/T20260423_G2383b931/34_RealWorldQA.pkl new file mode 100644 index 0000000000000000000000000000000000000000..526cc56906d6c18d95cd33747148b479f4ac0f41 --- /dev/null +++ b/no23_1round/T20260423_G2383b931/34_RealWorldQA.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69186693d551f9a794309aad1c0e9466267f69a6f69d4c9bec9b66431dd9dfa7 +size 3803 diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet.xlsx b/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..9039b9fffc719163ac9044b0161edfc091256428 Binary files /dev/null and b/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet.xlsx differ diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl b/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl new file mode 100644 index 0000000000000000000000000000000000000000..0de3325279798b64fd41664d3bb32260bc639be8 --- /dev/null +++ b/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582b7a615f363bfc5929c771e86ddee9ccb131dc6dce916122bf206f94dbccb0 +size 8683 diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx b/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..4832d2b54bf14492862be2b2ee1adaea9239ffce Binary files /dev/null and b/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx differ diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv b/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv new file mode 100644 index 0000000000000000000000000000000000000000..15c09ac62134d287d41c6f518673599cb64acc91 --- /dev/null +++ b/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv @@ -0,0 +1,8 @@ +"Category","tot","acc" +"rec","187","66.25668449197863" +"ocr","108","80.37037037037038" +"know","84","48.095238095238074" +"gen","80","52.12499999999998" +"spat","75","76.39999999999996" +"math","26","83.46153846153845" +"Overall","218","67.79816513761476" diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv b/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv new file mode 100644 index 0000000000000000000000000000000000000000..d321b93c24735f9d25c5576b8a487ee1855b8689 --- /dev/null +++ b/no23_1round/T20260423_G2383b931/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv @@ -0,0 +1,18 @@ +"Category","tot","acc" +"ocr_math","11","81.81818181818183" +"ocr_spat_math","14","90.71428571428572" +"rec_ocr_spat_math","1","0.0" +"rec_spat","12","65.83333333333333" +"ocr_spat","26","76.92307692307693" +"rec_ocr_spat","7","55.714285714285715" +"ocr_know_spat","3","100.0" +"rec_ocr","4","100.0" +"rec_know_spat","2","50.0" +"ocr","108","80.37037037037038" +"rec","187","66.25668449197863" +"rec_know","9","38.88888888888889" +"rec_know_gen","62","42.09677419354839" +"rec_ocr_know_gen","8","85.0" +"rec_ocr_gen_spat","8","88.75" +"ocr_gen_spat","2","85.00000000000001" +"Overall","218","67.79816513761476" diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_POPE.xlsx b/no23_1round/T20260423_G2383b931/checkpoint-48_POPE.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..beabe7f2b9a890651d553b56c9f18756700571c8 Binary files /dev/null and b/no23_1round/T20260423_G2383b931/checkpoint-48_POPE.xlsx differ diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_POPE_auxmatch.xlsx b/no23_1round/T20260423_G2383b931/checkpoint-48_POPE_auxmatch.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..cad0bc29996eaf9def9f79cb024fec629f6cb265 Binary files /dev/null and b/no23_1round/T20260423_G2383b931/checkpoint-48_POPE_auxmatch.xlsx differ diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_POPE_score.csv b/no23_1round/T20260423_G2383b931/checkpoint-48_POPE_score.csv new file mode 100644 index 0000000000000000000000000000000000000000..fb2229877623f298e6a6b9ff8f0d5d97ff536242 --- /dev/null +++ b/no23_1round/T20260423_G2383b931/checkpoint-48_POPE_score.csv @@ -0,0 +1,5 @@ +"split","Overall","acc","precision","recall" +"Overall","84.43496801705757","86.12167300380229","95.1923076923077","75.86206896551724" +"popular","84.61538461538461","86.36363636363636","95.65217391304348","75.86206896551724" +"adversarial","82.5","84.0","90.41095890410958","75.86206896551724" +"random","86.27450980392156","88.0","100.0","75.86206896551724" diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA.xlsx b/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..21e0273bc14ad26edd4fb0abaf73ea21bdbc5373 Binary files /dev/null and b/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA.xlsx differ diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl b/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b84bcdff06d9b685769e6b40064b0914af54e823 --- /dev/null +++ b/no23_1round/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 sha256:90a7a5fa4c592a03baefc0b18339c84a90e024c07723c0c411da3a5bcf2b3b5c +size 21295 diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx b/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..7b7a5d8a7a7083a13917c9611dcd99a82d2bcba7 Binary files /dev/null and b/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx differ diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA_acc.csv b/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..9463c242149e09d1b75c1560c7b68693c64e1462 --- /dev/null +++ b/no23_1round/T20260423_G2383b931/checkpoint-48_RealWorldQA_acc.csv @@ -0,0 +1,2 @@ +"split","Overall" +"none","0.6566666666666666" diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG.xlsx b/no23_1round/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..3ba2c502eb35b90e59110b7f8308b39b833a8c5d Binary files /dev/null and b/no23_1round/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG.xlsx differ diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl b/no23_1round/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..81b73226d259c4f2a12f1899ef643a0124f8077c --- /dev/null +++ b/no23_1round/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 sha256:2f2e46819bae6167ee68786f5457a7d9c5862fefa03b2d052284561ab41ce7f7 +size 18990 diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx b/no23_1round/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..0b68ab950ec6c6866a93ce51bfae1cfac32ec84d Binary files /dev/null and b/no23_1round/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx differ diff --git a/no23_1round/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_acc.csv b/no23_1round/T20260423_G2383b931/checkpoint-48_SEEDBench_IMG_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..913638508b7f438b5cddd1d5f8985a7535906ce0 --- /dev/null +++ b/no23_1round/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","0.7666666666666667","0.7938144329896907","0.8269230769230769","1.0","0.7727272727272727","0.7321428571428571","0.7169811320754716","0.5714285714285714","1.0","0.625" diff --git a/no23_1round/args.json b/no23_1round/args.json new file mode 100644 index 0000000000000000000000000000000000000000..eb8fb028f0fa55442d318383ff05ba8ef5863c78 --- /dev/null +++ b/no23_1round/args.json @@ -0,0 +1,376 @@ +{ + "output_dir": "/raid/icy/Thyme/output_dir_no23_1round/v3-20260402-144535", + "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": 32, + "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_no23_1round/v3-20260402-144535", + "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_no23_1round/v3-20260402-144535/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_no23_1round/v2-20260402-102051/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_no23_1round.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_no23_1round/v2-20260402-102051/checkpoint-243", + "rank": 0, + "global_world_size": 4, + "local_world_size": 4, + "model_suffix": "checkpoint-243", + "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/raid/icy/Thyme/output_dir_no23_1round/v2-20260402-102051/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_no23_1round/v2-20260402-102051/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_no23_1round/v3-20260402-144535', 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=32, 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_no23_1round/v3-20260402-144535', 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_no23_1round/v3-20260402-144535/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/no23_1round/chat_template.jinja b/no23_1round/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..6c226632394ae7474b0d4b13e15793eac2e21ee9 --- /dev/null +++ b/no23_1round/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/no23_1round/checkpoint-48_MMVet.xlsx b/no23_1round/checkpoint-48_MMVet.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..9039b9fffc719163ac9044b0161edfc091256428 Binary files /dev/null and b/no23_1round/checkpoint-48_MMVet.xlsx differ diff --git a/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl b/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl new file mode 100644 index 0000000000000000000000000000000000000000..0de3325279798b64fd41664d3bb32260bc639be8 --- /dev/null +++ b/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582b7a615f363bfc5929c771e86ddee9ccb131dc6dce916122bf206f94dbccb0 +size 8683 diff --git a/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx b/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..4832d2b54bf14492862be2b2ee1adaea9239ffce Binary files /dev/null and b/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct.xlsx differ diff --git a/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv b/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv new file mode 100644 index 0000000000000000000000000000000000000000..15c09ac62134d287d41c6f518673599cb64acc91 --- /dev/null +++ b/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score.csv @@ -0,0 +1,8 @@ +"Category","tot","acc" +"rec","187","66.25668449197863" +"ocr","108","80.37037037037038" +"know","84","48.095238095238074" +"gen","80","52.12499999999998" +"spat","75","76.39999999999996" +"math","26","83.46153846153845" +"Overall","218","67.79816513761476" diff --git a/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv b/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv new file mode 100644 index 0000000000000000000000000000000000000000..d321b93c24735f9d25c5576b8a487ee1855b8689 --- /dev/null +++ b/no23_1round/checkpoint-48_MMVet_Qwen2.5-VL-72B-Instruct_score_fine.csv @@ -0,0 +1,18 @@ +"Category","tot","acc" +"ocr_math","11","81.81818181818183" +"ocr_spat_math","14","90.71428571428572" +"rec_ocr_spat_math","1","0.0" +"rec_spat","12","65.83333333333333" +"ocr_spat","26","76.92307692307693" +"rec_ocr_spat","7","55.714285714285715" +"ocr_know_spat","3","100.0" +"rec_ocr","4","100.0" +"rec_know_spat","2","50.0" +"ocr","108","80.37037037037038" +"rec","187","66.25668449197863" +"rec_know","9","38.88888888888889" +"rec_know_gen","62","42.09677419354839" +"rec_ocr_know_gen","8","85.0" +"rec_ocr_gen_spat","8","88.75" +"ocr_gen_spat","2","85.00000000000001" +"Overall","218","67.79816513761476" diff --git a/no23_1round/checkpoint-48_RealWorldQA.xlsx b/no23_1round/checkpoint-48_RealWorldQA.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..21e0273bc14ad26edd4fb0abaf73ea21bdbc5373 Binary files /dev/null and b/no23_1round/checkpoint-48_RealWorldQA.xlsx differ diff --git a/no23_1round/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl b/no23_1round/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b84bcdff06d9b685769e6b40064b0914af54e823 --- /dev/null +++ b/no23_1round/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90a7a5fa4c592a03baefc0b18339c84a90e024c07723c0c411da3a5bcf2b3b5c +size 21295 diff --git a/no23_1round/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx b/no23_1round/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..7b7a5d8a7a7083a13917c9611dcd99a82d2bcba7 Binary files /dev/null and b/no23_1round/checkpoint-48_RealWorldQA_Qwen2.5-VL-72B-Instruct_result.xlsx differ diff --git a/no23_1round/checkpoint-48_RealWorldQA_acc.csv b/no23_1round/checkpoint-48_RealWorldQA_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..9463c242149e09d1b75c1560c7b68693c64e1462 --- /dev/null +++ b/no23_1round/checkpoint-48_RealWorldQA_acc.csv @@ -0,0 +1,2 @@ +"split","Overall" +"none","0.6566666666666666" diff --git a/no23_1round/checkpoint-48_SEEDBench_IMG.xlsx b/no23_1round/checkpoint-48_SEEDBench_IMG.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..3ba2c502eb35b90e59110b7f8308b39b833a8c5d Binary files /dev/null and b/no23_1round/checkpoint-48_SEEDBench_IMG.xlsx differ diff --git a/no23_1round/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl b/no23_1round/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl new file mode 100644 index 0000000000000000000000000000000000000000..81b73226d259c4f2a12f1899ef643a0124f8077c --- /dev/null +++ b/no23_1round/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f2e46819bae6167ee68786f5457a7d9c5862fefa03b2d052284561ab41ce7f7 +size 18990 diff --git a/no23_1round/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx b/no23_1round/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..0b68ab950ec6c6866a93ce51bfae1cfac32ec84d Binary files /dev/null and b/no23_1round/checkpoint-48_SEEDBench_IMG_Qwen2.5-VL-72B-Instruct_result.xlsx differ diff --git a/no23_1round/checkpoint-48_SEEDBench_IMG_acc.csv b/no23_1round/checkpoint-48_SEEDBench_IMG_acc.csv new file mode 100644 index 0000000000000000000000000000000000000000..913638508b7f438b5cddd1d5f8985a7535906ce0 --- /dev/null +++ b/no23_1round/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","0.7666666666666667","0.7938144329896907","0.8269230769230769","1.0","0.7727272727272727","0.7321428571428571","0.7169811320754716","0.5714285714285714","1.0","0.625" diff --git a/no23_1round/config.json b/no23_1round/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d69d8df225fac8280afdc38c657b817439342a47 --- /dev/null +++ b/no23_1round/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/no23_1round/generation_config.json b/no23_1round/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..02d10ad915167bd3c6a69cdbd79f7e1b27e9d103 --- /dev/null +++ b/no23_1round/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/no23_1round/global_step48/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/no23_1round/global_step48/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f99eb7fbb730717c742845023a4c41b0801f672 --- /dev/null +++ b/no23_1round/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:b05554845942e7dff29b3c3d3730508c5a4bb629890f2cf4b390598fcc3f35c6 +size 22846862028 diff --git a/no23_1round/global_step48/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/no23_1round/global_step48/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e93bbab522aef5f127d20fafdcc70ffd7cda2da1 --- /dev/null +++ b/no23_1round/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 sha256:2915c439e5ec059b5d6412658a1cfd20e99c7b6c96a7175a1852bded3b4530dc +size 22846863436 diff --git a/no23_1round/global_step48/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/no23_1round/global_step48/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fd88e61328aa65a5e191e191122c2ab2e98d7678 --- /dev/null +++ b/no23_1round/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 sha256:8b82e995c65639e76e7d96a80c6a60809a17bed1d3ae9d2193b4aaf2f06bf19d +size 22846863820 diff --git a/no23_1round/global_step48/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/no23_1round/global_step48/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba71bce67607ae7aa546d89eee4901a505d0c9b7 --- /dev/null +++ b/no23_1round/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 sha256:3f9c8352203a6c7a120f077eb6f43eafaa61f78faf68387ec0a935cde5c69389 +size 22846861708 diff --git a/no23_1round/global_step48/mp_rank_00_model_states.pt b/no23_1round/global_step48/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..88aff12a5d849d6d57a579779dc537ddfb7fa06e --- /dev/null +++ b/no23_1round/global_step48/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:777e8c0ffb4d587e502d629e652e6d2f6c6459540443dfc9ce7fcab2188f78e9 +size 16584598266 diff --git a/no23_1round/latest b/no23_1round/latest new file mode 100644 index 0000000000000000000000000000000000000000..32b61bf48e124ca282ba181c375b3ab4423b774d --- /dev/null +++ b/no23_1round/latest @@ -0,0 +1 @@ +global_step48 \ No newline at end of file diff --git a/no23_1round/model-00001-of-00004.safetensors b/no23_1round/model-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17064c122102fff768add1a2c05e732c515fc272 --- /dev/null +++ b/no23_1round/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:932699a919c6f31e831767c3df6839fde715f4eb803f8524e5b4b9d8a63b1c60 +size 4976698728 diff --git a/no23_1round/model-00002-of-00004.safetensors b/no23_1round/model-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91f3e02c04ceb2c072be745d65d3f8bc7a6b7eec --- /dev/null +++ b/no23_1round/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c896aaad43baa7abf2a5f6796ce1686de5b7ceeb9f80328722431c6bf70e24f +size 4932750984 diff --git a/no23_1round/model-00003-of-00004.safetensors b/no23_1round/model-00003-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d1cbe726ff35070938d69e960b26a90a81b11295 --- /dev/null +++ b/no23_1round/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1407b7859a8efe918c29e618905b6dbe7f82fbd36ff06337b8c1d6042210555c +size 4991495880 diff --git a/no23_1round/model-00004-of-00004.safetensors b/no23_1round/model-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab536c235ef9e4f75673033b14de04cb5b60b49d --- /dev/null +++ b/no23_1round/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85fd422f034a107687a3bc5103dc7e3ec00c758154ffcace33db897dc8081ff9 +size 1683468520 diff --git a/no23_1round/model.safetensors.index.json b/no23_1round/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..bd9e4e69e006586072470fe13428836fb86741dd --- /dev/null +++ b/no23_1round/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/no23_1round/preprocessor_config.json b/no23_1round/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..7f3b746825e5eef53ed8ed57a91df9e86ee62c0a --- /dev/null +++ b/no23_1round/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/no23_1round/processor_config.json b/no23_1round/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9e717d9bf475c411369034636e82e48cf79108a8 --- /dev/null +++ b/no23_1round/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/no23_1round/rng_state_0.pth b/no23_1round/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..25c968b44f64cbb72be6f6649ee277d3fa7097d0 --- /dev/null +++ b/no23_1round/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03269e9b7ea16cd98a78d6ea7a50b8454cbd266a053c02f734d27c4d0056b89d +size 15024 diff --git a/no23_1round/rng_state_1.pth b/no23_1round/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..955a80e651b1f8cb989b49c8b23425013715296e --- /dev/null +++ b/no23_1round/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4509495bd2a081212bbe15f7d1784af338aff3aadb1c5fe444c3f44626992d0 +size 15024 diff --git a/no23_1round/rng_state_2.pth b/no23_1round/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa005c74cc3eb2519657be3c494f323e7c8d1d79 --- /dev/null +++ b/no23_1round/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104638f895e79f68373b82e8ca745e8070a37851d21a073a0fa5ae1db47649d6 +size 15024 diff --git a/no23_1round/rng_state_3.pth b/no23_1round/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..104e9ccfd2036951dd3d763f5838f18c13eb7f46 --- /dev/null +++ b/no23_1round/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:765f109d2f595ccad091f8175cdf531d159f08de0ff5196e08c6bb1d0ceda0d5 +size 15024 diff --git a/no23_1round/scheduler.pt b/no23_1round/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..be6c8aae0e741a986d4254ed90c24030bc3a0975 --- /dev/null +++ b/no23_1round/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39788f5c12e60a3abb9757db4a3ac31b72797ca865bcb95bcdb8880929fce9a4 +size 1064 diff --git a/no23_1round/tokenizer.json b/no23_1round/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..34510ff0037cd50428af467a17ead5a96140a32c --- /dev/null +++ b/no23_1round/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/no23_1round/tokenizer_config.json b/no23_1round/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a32ee6b01c7145a5b88d42f6c19a4b6ff7f682d7 --- /dev/null +++ b/no23_1round/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/no23_1round/trainer_state.json b/no23_1round/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..ed8c33a4c1a53ddc2e90945e60aaea5df9d6409e --- /dev/null +++ b/no23_1round/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": 0.06464646464646465, + "grad_norm": 2.7468647956848145, + "learning_rate": 3.333333333333333e-07, + "loss": 0.8075233101844788, + "step": 1, + "token_acc": 0.7789686590299043 + }, + { + "epoch": 0.32323232323232326, + "grad_norm": 2.833563804626465, + "learning_rate": 9.95134034370785e-07, + "loss": 0.8278259634971619, + "step": 5, + "token_acc": 0.77555910696737 + }, + { + "epoch": 0.6464646464646465, + "grad_norm": 2.546499252319336, + "learning_rate": 9.414737964294634e-07, + "loss": 0.8087774276733398, + "step": 10, + "token_acc": 0.7784151309114588 + }, + { + "epoch": 0.9696969696969697, + "grad_norm": 1.9373090267181396, + "learning_rate": 8.34565303179429e-07, + "loss": 0.788428258895874, + "step": 15, + "token_acc": 0.7792703429962006 + }, + { + "epoch": 1.2585858585858585, + "grad_norm": 1.6739438772201538, + "learning_rate": 6.87303296707956e-07, + "loss": 0.7679871082305908, + "step": 20, + "token_acc": 0.784328294085834 + }, + { + "epoch": 1.5818181818181818, + "grad_norm": 1.5068683624267578, + "learning_rate": 5.174497483512505e-07, + "loss": 0.7111423969268799, + "step": 25, + "token_acc": 0.7940434407203489 + }, + { + "epoch": 1.905050505050505, + "grad_norm": 1.2880864143371582, + "learning_rate": 3.454915028125263e-07, + "loss": 0.7116360664367676, + "step": 30, + "token_acc": 0.7931073746536608 + }, + { + "epoch": 2.193939393939394, + "grad_norm": 1.162566900253296, + "learning_rate": 1.9216926233717084e-07, + "loss": 0.7041250705718994, + "step": 35, + "token_acc": 0.7963282807966519 + }, + { + "epoch": 2.517171717171717, + "grad_norm": 1.1574581861495972, + "learning_rate": 7.597595192178702e-08, + "loss": 0.7051266193389892, + "step": 40, + "token_acc": 0.7935210972359477 + }, + { + "epoch": 2.8404040404040405, + "grad_norm": 1.050368309020996, + "learning_rate": 1.0926199633097154e-08, + "loss": 0.684901237487793, + "step": 45, + "token_acc": 0.7989938830043644 + } + ], + "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": 4.0826558339035955e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/no23_1round/training_args.bin b/no23_1round/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1113ce5eb9fa49508936de315ab5015fa56d99cd --- /dev/null +++ b/no23_1round/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3786338bb9e6eec5c2f60c32f5c5d701608c6302b816847c5aab4d13f64831e +size 8312 diff --git a/no23_1round/zero_to_fp32.py b/no23_1round/zero_to_fp32.py new file mode 100644 index 0000000000000000000000000000000000000000..e69ecd9acb5a235ffbf927091051106d902b3d39 --- /dev/null +++ b/no23_1round/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)