135 Commits

Author SHA1 Message Date
hiyouga
7f71276ad8 add docstrings, refactor logger
Former-commit-id: c34e489d71f8f539028543ccf8ee92cecedd6276
2024-09-08 00:56:56 +08:00
hiyouga
27547355e6 tiny fix
Former-commit-id: c0e9c0484dae6db93cef5048bad827ff22b1986a
2024-09-05 23:41:16 +08:00
hiyouga
9bdba2f6a8 add e2e tests
Former-commit-id: 0156a37450604641c4f5f9756ad84324698fc88c
2024-09-05 21:52:28 +08:00
hoshi-hiyouga
d6ce902d80 Merge pull request #5372 from LDLINGLINGLING/main
增加了对minicpm3.0的适配'

Former-commit-id: 2e3c221d9c87bd59f48648be8878b7b50347280f
2024-09-05 21:35:42 +08:00
liudan
ce6dcf3600 根据代码规范修改了代码
Former-commit-id: fe5351980b42e0e38175b0da2401a61b3807fa7c
2024-09-05 20:17:55 +08:00
hiyouga
72222d1598 support Yi-Coder models
Former-commit-id: ea3f1659e70541c4fa8b7079a0a8c94fce9a41c8
2024-09-05 03:12:24 +08:00
hiyouga
1874d579c5 video datasets
Former-commit-id: 33f28ce82d9e44d2615909250dc56d6a4a03cd99
2024-09-05 02:04:17 +08:00
liudan
c692339020 增加了对minicpm3.0的适配'
Former-commit-id: 4ad3a761af2452ef3f6c61190b7e47c9ea5227b9
2024-09-04 23:10:05 +08:00
hiyouga
af178cbcd1 update get template
Former-commit-id: 21ea0d0786f91c0bce79630963e66b815a6792a0
2024-09-04 22:36:20 +08:00
hoshi-hiyouga
5d85be31ca Merge pull request #5323 from naem1023/feat/add-dataset-map-batch-size-argument
Add batch size of map function in the preprocessed dataset

Former-commit-id: c3428c5807500d087cdee4386798e10e39c9cf30
2024-09-04 22:09:36 +08:00
hoshi-hiyouga
372b71c847 fix #5228
Former-commit-id: 0d332ca8d0987c0331361934ab110fafa6402a7e
2024-09-04 19:10:30 +08:00
hiyouga
f4dd429cbf fix #5344
Former-commit-id: 9d445c0b5be5ccc0e6d1979e76a869ddf92d9534
2024-09-04 03:06:06 +08:00
hiyouga
7056087e92 lazy image load
Former-commit-id: cdd733b575411e003bc5ffd6560dd8eff8aa09cf
2024-09-04 02:27:08 +08:00
hiyouga
5019c6148b fix #5338
Former-commit-id: a66ddfea218feefde50fa097d20b4bcbe89ab791
2024-09-03 17:45:17 +08:00
naem1023
3622856994 feat: add batch size of map function in the preprocessed dataset
Former-commit-id: 94b6cf06c2f84d0619b1a2dccaf8abb51de9951c
2024-09-02 13:52:47 +09:00
hiyouga
f203a9d78e tiny fix
Former-commit-id: 8b4f408da110d74285bae20bbd969013a979964b
2024-09-02 01:33:22 +08:00
hiyouga
bae73e676c add image num check
Former-commit-id: 15201113bf16b748c0a758c7a5b363da8272e0e6
2024-09-02 01:31:36 +08:00
hiyouga
60cf12727b add rlhf-v dataset
Former-commit-id: 3fd18fc34a0c994a738504746abfd5548e002437
2024-09-01 22:57:41 +08:00
hiyouga
559b84dceb fix bug
Former-commit-id: 6e19e56000dd18d5faf84ceabce8d7708ff21e4d
2024-09-01 21:07:49 +08:00
hiyouga
7e4c5d4bb3 fix mixed mm inputs and rlhf-v
Former-commit-id: 7c248fac20bf85d57a91132ce7a793c7f84e9218
2024-09-01 20:52:47 +08:00
hiyouga
43654028eb add test mm plugin
Former-commit-id: ddea5cca5a3174de1dcc7fdee8ec69e77700b6bf
2024-08-31 01:53:38 +08:00
hiyouga
665db18661 tiny fix
Former-commit-id: 830511a6d0216da99520aee8b3a753d347a71fa9
2024-08-30 03:21:50 +08:00
hiyouga
c62a6ca59d refactor mm training
Former-commit-id: 179c0558699e287cbf38a2d73bff47e86d589c5a
2024-08-30 02:14:31 +08:00
hoshi-hiyouga
7466fd4387 fix bug
Former-commit-id: 365e6df71509569f59c40743c115f1a4b945ef0f
2024-08-30 02:05:26 +08:00
simonJJJ
5b4b60cfb5 update
Former-commit-id: a968a416d5e513320c97109229ca1e6ddc003cb1
2024-08-28 20:22:46 +08:00
simonJJJ
0f3d54d8a0 initial-commit
Former-commit-id: b6a39847a10b417b09db4b5512dd835e9e4ce928
2024-08-28 16:51:35 +08:00
hoshi-hiyouga
388f0a6e05 Merge pull request #5156 from YeQiuO/main
fix Llama-template's system prompt bug

Former-commit-id: 0b57175d3bd029675dae2f55995b7eeb4e9adc7a
2024-08-20 00:09:03 +08:00
hoshi-hiyouga
8c13c02c55 Update template.py
Former-commit-id: f5a075cb1c90f05bb0de26c6aea718f556c54623
2024-08-20 00:03:33 +08:00
hoshi-hiyouga
b681f24f43 Update template.py
Former-commit-id: c6822a217e1c296f4aedd9a2c7610acd1dbd443e
2024-08-19 23:40:16 +08:00
Huiyu Chen
22a79c169d Add SailorLLM template
Former-commit-id: a594abe0321a718394a97b5a48ded16e2012c1f0
2024-08-15 15:10:14 +08:00
“Wzw”
e734222373 fix Llama-template's system prompt bug
Former-commit-id: 2e3eddcd0918b0c968ded0df7c82e3dcff870381
2024-08-12 19:22:12 +08:00
hiyouga
5af32ce705 follow #5115
Former-commit-id: 7d917e03e2df570139bae18227d9c7303a12de2a
2024-08-09 18:03:00 +08:00
hoshi-hiyouga
4e8861e653 Merge pull request #5115 from YeQiuO/main
fix: `Train on the last turn only` truncate bug
Former-commit-id: 2c6dae45f7a7b72c961489ac407b1b444ab7752e
2024-08-09 17:58:27 +08:00
hoshi-hiyouga
46f834ec75 Update template.py
Former-commit-id: ae2a5221c109ae3474d219c37433be767abbee91
2024-08-09 16:27:42 +08:00
“Wzw”
6ec64a7e56 mask_history args verify valid
Former-commit-id: 2f8388b4f4195d934400ad9267d72e10ca4105a3
2024-08-08 10:12:01 +08:00
“Wzw”
d71446e387 fix mask_history tiny bug
Former-commit-id: cac07aac6196be026f723b2397a343d4fb675973
2024-08-08 10:09:33 +08:00
moontidef
7b4f5d3b21 fix: fix the deepseekcoder template to avoid repeat problem
Former-commit-id: 56294831115f095135f72490a8a435434b2f0a11
2024-08-05 23:55:45 +08:00
hoshi-hiyouga
9f74d36ba4 Merge pull request #4892 from piamo/main
update deepseek template

Former-commit-id: 3233efc8404972098665286d9dec7312dd6ecfab
2024-07-26 11:49:34 +08:00
hiyouga
ff5ba97970 fix #4928
Former-commit-id: 6d557e8959678f9d4edbcb3d5a6dfba14b429b18
2024-07-24 17:00:29 +08:00
hiyouga
a770afbff2 fix flashattn + packing
Former-commit-id: 4adc6ce4abc718c25f39b316bfc3352d0d01ed1e
2024-07-21 17:07:45 +08:00
huangpan.foo
b1a5bf025b update deepseek template
Former-commit-id: f5ca86ec95bb301df42ffaa6923fc3037a224e34
2024-07-19 15:02:54 +08:00
hiyouga
4c1513a845 follow #4878 fix #4684
Former-commit-id: 4715e5c5b8040b21e5f401f7e969b9fd2757d520
2024-07-18 22:06:12 +08:00
Shiyu Zhang
c1e1918db1 仅仅训练最后一轮对话
Former-commit-id: ab6198e4c099edeb1a400f58729cd617e8cd8e50
2024-07-18 15:30:25 +08:00
hoshi-hiyouga
68365045b4 Merge pull request #4691 from codemayq/feature-suppot-eval-dataset
add eval dataset support

Former-commit-id: 51eb379b44fad0336fc96c329ec98dc4528b9c2c
2024-07-15 01:00:34 +08:00
hoshi-hiyouga
0bc52c0aae Update preprocess.py
Former-commit-id: da92f4a1b9c12a8e2489b964baba5e2c8e739ef1
2024-07-15 00:55:36 +08:00
hoshi-hiyouga
6bf2663b8e Update parser.py
Former-commit-id: 145687997c86b8785e37dd60fbb9f3a5986730a6
2024-07-15 00:55:21 +08:00
hoshi-hiyouga
d337de668e Update data_utils.py
Former-commit-id: 5c2a0e3b1d1afd2a9219d935d3421fffffc3a2c9
2024-07-15 00:54:34 +08:00
hoshi-hiyouga
ec372f91e9 Update loader.py
Former-commit-id: 860e3eb374947b72dcae88cab0a93ef561e3bfb3
2024-07-15 00:50:06 +08:00
hoshi-hiyouga
ee17741591 Update parser.py
Former-commit-id: b9760df588e64270a140d9111241c62c1cefe781
2024-07-14 23:04:34 +08:00
hiyouga
5ab997d484 fix gemma2 attention
Former-commit-id: aeafc68e169ae0ea5939cc81cb0cf89f0ca044b6
2024-07-13 23:33:45 +08:00