hiyouga
|
4117f38827
|
fix chatglm3 template
|
2023-10-27 21:12:06 +08:00 |
|
hiyouga
|
4600c29e93
|
update readme
|
2023-10-27 19:19:03 +08:00 |
|
hiyouga
|
1c0ab9a908
|
support chatglm3
|
2023-10-27 19:16:28 +08:00 |
|
hiyouga
|
3fe7df628d
|
support dataset cache
|
2023-10-26 21:48:45 +08:00 |
|
hiyouga
|
838ed9aa87
|
fix #1287
|
2023-10-26 17:49:41 +08:00 |
|
hiyouga
|
aff9363ce3
|
fix #1285
|
2023-10-26 16:34:52 +08:00 |
|
hiyouga
|
d357e08b58
|
Update wechat.jpg
|
2023-10-24 16:02:12 +08:00 |
|
hiyouga
|
2caf91f824
|
remove filter in preprocess
|
2023-10-23 23:46:02 +08:00 |
|
hiyouga
|
7de7174ce3
|
update neftune logic
|
2023-10-22 17:42:13 +08:00 |
|
hiyouga
|
11b55a3270
|
fix webui
|
2023-10-22 17:24:56 +08:00 |
|
hiyouga
|
f793ca0a2c
|
add new options in webui
|
2023-10-22 17:17:58 +08:00 |
|
hiyouga
|
b79ca8781e
|
fix recursion error
|
2023-10-22 16:28:37 +08:00 |
|
hiyouga
|
7b4acf7265
|
reimplement neftune
|
2023-10-22 16:15:08 +08:00 |
|
hoshi-hiyouga
|
b42a145253
|
Merge pull request #1252 from anvie/neftune
add NEFTune optimization
|
2023-10-22 15:59:20 +08:00 |
|
anvie
|
57fb40aa04
|
add NEFTune optimization
|
2023-10-21 13:24:10 +07:00 |
|
hiyouga
|
8fdff07e1f
|
fix openchat template
|
2023-10-21 01:25:42 +08:00 |
|
hiyouga
|
641ffa2f6e
|
fix tokenizer padding side in evaluate.py
|
2023-10-21 00:30:04 +08:00 |
|
hiyouga
|
b665e9e133
|
fix #1232
|
2023-10-20 23:28:52 +08:00 |
|
hiyouga
|
0fcf66049d
|
fix #1215
|
2023-10-19 16:19:21 +08:00 |
|
hiyouga
|
7a11a42dfd
|
fix #1218
|
2023-10-19 16:17:41 +08:00 |
|
hiyouga
|
cb0edd2302
|
fix #1228
|
2023-10-19 15:54:10 +08:00 |
|
hiyouga
|
6496a99b7d
|
fix #1217
|
2023-10-19 15:52:24 +08:00 |
|
hiyouga
|
1611fad6bc
|
rename webui
|
2023-10-16 15:16:24 +08:00 |
|
hiyouga
|
85480f2e86
|
fix #1197
|
2023-10-16 15:13:46 +08:00 |
|
hoshi-hiyouga
|
5f83a6e72c
|
Update README_zh.md
|
2023-10-16 00:28:27 +08:00 |
|
hoshi-hiyouga
|
beacb798ea
|
Update README.md
|
2023-10-16 00:23:37 +08:00 |
|
hiyouga
|
7a53188048
|
release v0.2.0
|
2023-10-15 20:49:43 +08:00 |
|
hiyouga
|
f5d0da4d2a
|
update readme
|
2023-10-15 20:28:14 +08:00 |
|
hoshi-hiyouga
|
25d326e135
|
Update README.md
|
2023-10-15 20:23:22 +08:00 |
|
hiyouga
|
a6a04be2e6
|
fix config, #1191
|
2023-10-15 18:28:45 +08:00 |
|
hiyouga
|
0d63584c03
|
disable tqdm in webui mode
|
2023-10-15 16:18:25 +08:00 |
|
hiyouga
|
ea82f8a82a
|
refactor export, fix #1190
|
2023-10-15 16:01:48 +08:00 |
|
hiyouga
|
273745f9b9
|
fix eval resuming in webui
|
2023-10-15 15:45:38 +08:00 |
|
hiyouga
|
3ad8c92eca
|
tiny fix
|
2023-10-15 05:02:48 +08:00 |
|
hiyouga
|
1e9401744c
|
fix callback
|
2023-10-15 04:59:44 +08:00 |
|
hoshi-hiyouga
|
a63a1cebb2
|
Merge pull request #1186 from hiyouga/dev
Support Web UI resuming training
|
2023-10-15 04:53:14 +08:00 |
|
hiyouga
|
accde3cd39
|
implement webui resuming training
|
2023-10-15 04:52:19 +08:00 |
|
hiyouga
|
fde05cacfc
|
fix bugs in webui
|
2023-10-15 03:41:58 +08:00 |
|
hiyouga
|
7ed1fa6fe9
|
refactor webui
|
2023-10-15 03:06:21 +08:00 |
|
hiyouga
|
c874e764b8
|
fix loading dtype
|
2023-10-14 20:15:24 +08:00 |
|
hiyouga
|
01d8cb1ca7
|
fix #1176 #1177
|
2023-10-14 20:00:17 +08:00 |
|
hiyouga
|
af18b0dce7
|
fix #1184
|
2023-10-14 19:20:11 +08:00 |
|
hiyouga
|
b240b6792f
|
fix webui
|
2023-10-13 16:27:59 +08:00 |
|
hiyouga
|
cb42676694
|
update readme
|
2023-10-13 13:53:43 +08:00 |
|
hiyouga
|
c4102f306a
|
update discord link
|
2023-10-12 21:44:28 +08:00 |
|
hiyouga
|
197c754d73
|
rename repository
|
2023-10-12 21:42:29 +08:00 |
|
hiyouga
|
932e3fee3a
|
Update wechat.jpg
|
2023-10-12 20:45:58 +08:00 |
|
hiyouga
|
11bd271364
|
fix ppo args
|
2023-10-11 23:40:50 +08:00 |
|
hiyouga
|
2818af0b09
|
refactor model_dtype, fix PPO trainer
|
2023-10-11 23:16:01 +08:00 |
|
hiyouga
|
5310e4d182
|
add averaging in evaluation
|
2023-10-10 23:16:31 +08:00 |