133 Commits

Author SHA1 Message Date
hiyouga
4738d002c7 tiny fix
Former-commit-id: 37aa7099dff2a9a7b52e259dac92de41ce606946
2023-12-01 15:58:50 +08:00
hoshi-hiyouga
a51253fea2 Merge pull request #1690 from billvsme/main
Improve get_current_device

Former-commit-id: c3b8cc27c91248a7381b3333abf099064412dc1a
2023-12-01 15:44:35 +08:00
hiyouga
304ec9ec6a fix #1696
Former-commit-id: 722ae14a652af34d9b91f9459e613d7959ecaa7e
2023-12-01 15:34:50 +08:00
billvsme
7b45f5068f improve get_current_device
Former-commit-id: 2b07815e7fc8dc6ad0a7e9eccdd6681fbab35f3c
2023-11-30 22:40:35 +08:00
hiyouga
7ef8f46591 add models
Former-commit-id: b9eaadde8b5f4b9f89fa7bb910b325fcf9c84434
2023-11-30 19:16:13 +08:00
hiyouga
670ee3934f fix #1659
Former-commit-id: e4123129aae59f4123d53c1f5320e3d5e09ae26d
2023-11-28 20:52:28 +08:00
hiyouga
953a562ec1 support Yi-34B-Chat models
Former-commit-id: 1751a79c27e7fc13e76a731a061dc0c10d828cda
2023-11-23 19:31:49 +08:00
hiyouga
28258aecd2 update ppo trainer
Former-commit-id: caa525a5c6f228b9ad71387d1fe4f1c2ffa2479e
2023-11-20 21:39:15 +08:00
hiyouga
6889f044fb fix #1558
Former-commit-id: 263b2b24c8a649b51fa5ae768a24e67def8e0e96
2023-11-19 14:15:47 +08:00
hiyouga
85c4ccfef9 fix packages
Former-commit-id: c93175d18ad9a4b7b61629153acabf8d0c978dfc
2023-11-17 16:11:48 +08:00
Shaowen Wang
07f934566a Fix: Change rouge-chinese package name to rouge_chinese
To reproduce:
python:
importlib.util.find_spec('rouge-chinese') -> None
importlib.util.find_spec('rouge_chinese') -> ModuleSpec(name='rouge_chinese'...)
from rouge_chinese import Rouge
print(Rouge.__module__) -> rouge_chinese
Former-commit-id: a78b11d944b6cb7dbe2a1d8a24d240e196aa530a
2023-11-16 20:12:35 -06:00
hiyouga
dab9385297 fix bug in web ui
Former-commit-id: a598f145ec903dd2b2c984d951b6c450b142ece5
2023-11-16 15:21:24 +08:00
hiyouga
df83def566 update ppo and demo in webui
Former-commit-id: de7571704c82121db13e3fc907379d2453100191
2023-11-16 14:55:26 +08:00
hiyouga
e59a3d71e0 tiny fix
Former-commit-id: d65519d8a44b73bbb713741c23465f13c35c83f5
2023-11-16 03:27:19 +08:00
hiyouga
de3a84ac59 fix rlhf callback
Former-commit-id: f5485452d660caef56474cb7dc37abbe4f34599e
2023-11-16 03:26:19 +08:00
hiyouga
7a3a0144a5 support full-parameter PPO
Former-commit-id: 4af967d69475e1c9fdf1a7983cd6b83bd431abff
2023-11-16 02:08:04 +08:00
hiyouga
2162c37e41 update readme and constants
Former-commit-id: 7d83e3dd9101a4fdd0b589d0c1f7b609c0feecd1
2023-11-15 18:04:37 +08:00
hiyouga
09a4474e7f disentangle model from tuner and rename modules
Former-commit-id: 02cbf91e7e424f8379c1fed01b82a5f7a83b6947
2023-11-15 16:29:09 +08:00
hiyouga
ec334f5891 release v0.2.2, fix #1478 #1466
Former-commit-id: c9534c411716e1dceb54c5eb35fe845c93ee2973
2023-11-13 23:09:05 +08:00
hiyouga
64fc9ba678 refactor evaluation, upgrade trl to 074
Former-commit-id: ed09ebe2c1926ffdb0520b3866f7fd03a9aed046
2023-11-13 22:20:35 +08:00
hiyouga
989eccd286 fix flashattn warning
Former-commit-id: 6eb095d39bd82fdbdb729a0ea57fc7246e3a60d6
2023-11-10 18:34:54 +08:00
hiyouga
178b85ff9a refactor constants
Former-commit-id: a4d4c3fd35276f20e3b354e9d13ea971029c8775
2023-11-10 14:16:10 +08:00
hiyouga
48ec5355f9 add template, modify datasets
Former-commit-id: 81e54beb4d0f792f4fd7f450643caaf10f2f0b7d
2023-11-09 15:53:23 +08:00
hiyouga
f7f0c3070e delete file
Former-commit-id: 7d6355db0fd5809b99f3fa42753cf4dffd251fd1
2023-11-07 16:20:12 +08:00
hiyouga
2eb65d21ac upgrade peft, fix #1088 #1411
Former-commit-id: aa7d104f8e050d12cb8f585bc8a52c850995500f
2023-11-07 16:13:36 +08:00
hiyouga
2c48e798ca update templates
Former-commit-id: 85be2e242b062283f192c4c4d0715dc1e8a68589
2023-11-06 12:25:47 +08:00
hiyouga
2a8892b785 fix deepseek template
Former-commit-id: 1fdbcdad9a1cdb20299350efd87a8e5cb8c625a3
2023-11-05 13:08:46 +08:00
hiyouga
ee3b33ff03 support deepseek coder #1378
Former-commit-id: ae0c829917b9de10e71199c85c77a52cdcd2b7b3
2023-11-05 12:51:03 +08:00
hiyouga
db06fcfc84 fix #1316
Former-commit-id: 88a753fe80e277007bac2264aee24024e18f2314
2023-10-31 11:32:08 +08:00
hiyouga
0f727b393e update constants
Former-commit-id: ebacbb1072045924a7e335cc9dda488d6f0be8b3
2023-10-29 13:30:20 +08:00
hiyouga
7da2aad6ee fix vicuna template
Former-commit-id: a98eda0803e4b73a24f12d848e14161451921e98
2023-10-27 22:15:25 +08:00
hiyouga
6f09f50d02 fix chatglm3 template
Former-commit-id: 69bcbc9f6c98e4f4ad97ec0306b33ab21923d311
2023-10-27 21:12:06 +08:00
hiyouga
f7635c1afc support chatglm3
Former-commit-id: ba82e13bbeed3b262d301196b1860d73f319401d
2023-10-27 19:16:28 +08:00
hiyouga
6a955ccf4f fix openchat template
Former-commit-id: 88b9b657bc50495ac4c42f64195fc652fe4ca3df
2023-10-21 01:25:42 +08:00
hiyouga
d602f06882 fix #1232
Former-commit-id: 49975755d47344e362145c52548fdda8783f2c0c
2023-10-20 23:28:52 +08:00
hiyouga
68330eab2a fix eval resuming in webui
Former-commit-id: b28b53cd06777f213ef7b925a914ff5fd357ade1
2023-10-15 15:45:38 +08:00
hiyouga
7070f3969d tiny fix
Former-commit-id: 47b7b34357708a5354d542ddc239146c6417d718
2023-10-15 05:02:48 +08:00
hiyouga
e4727ab155 fix callback
Former-commit-id: 51208655a8c1d66551b7b644247321a3583debdc
2023-10-15 04:59:44 +08:00
hiyouga
31e3805fb8 implement webui resuming training
Former-commit-id: 2d41672ef52414c56c50c8b4fdc442797ba682e9
2023-10-15 04:52:19 +08:00
hiyouga
3198a7e5f4 refactor model_dtype, fix PPO trainer
Former-commit-id: 3e17ee5afbcb823a7c9a2f91864b3750cd79edb4
2023-10-11 23:16:01 +08:00
hiyouga
bd8ea09479 fix aquila template, repair sft packing mechanism
Former-commit-id: 8c82cfa5dd4bec957426b5bf176d242c77552ab0
2023-10-10 18:49:55 +08:00
hiyouga
f74d600497 fix flash shift short attention
Former-commit-id: e44ad23eafa39b3ac0400b6f97cd440106a87f44
2023-10-09 17:54:48 +08:00
hiyouga
e387a50475 fix shift short attention
Former-commit-id: 9a49cce8e6f6b222f74a07bdab40efee6a77b0f1
2023-10-09 17:07:46 +08:00
hiyouga
728dfb1be7 fix #1068 #1074
Former-commit-id: 26c6bfd21de06cc56be9a58e2ef69045ea70cc14
2023-09-28 14:39:16 +08:00
hiyouga
21a454fa6c tiny fix
Former-commit-id: 35b355b76d2a8f8adf3750a905224e52d03d218f
2023-09-28 01:03:04 +08:00
hiyouga
22c6c27f78 tiny fix
Former-commit-id: 7451b2ae7e58d0f1857f01a037672a8c53b1bd0d
2023-09-28 01:02:11 +08:00
hiyouga
aecbb43096 fix #1064
Former-commit-id: fd4660aa72d981d7efdad465f24a59358626c975
2023-09-28 00:53:29 +08:00
hiyouga
1c150995ae fix layer norm dtype
Former-commit-id: 67af21961b68d9b54d07b09e444c7140869f26da
2023-09-28 00:25:55 +08:00
hiyouga
20130b486c support LongLoRA
Former-commit-id: 0832ed37e7947d699f17375648a52f80752c2b6b
2023-09-27 21:55:50 +08:00
hiyouga
35d1921081 add MMLU and C-Eval script
Former-commit-id: 3403f876127b4b99c5e3edb2834cc3b9a3a0063f
2023-09-23 00:34:17 +08:00