kyy/llm_trainer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
532 Commits 1 Branch 0 Tags
bbbce1f516840f722247edd37057d16502ea0557
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
hiyouga bbbce1f516 fix imports 2023-11-15 16:47:45 +08:00
hiyouga 4736344eb1 disentangle model from tuner and rename modules 2023-11-15 16:29:09 +08:00
hiyouga 2f02f688e1 fix #1507 2023-11-15 16:22:32 +08:00
hiyouga 829e879e04 Update cal_lr.py 2023-11-14 21:14:42 +08:00
hiyouga 5619e76dc5 Update cal_lr.py 2023-11-14 21:13:01 +08:00
hiyouga fcb2daf7f3 Update cal_lr.py 2023-11-14 21:09:30 +08:00
hiyouga 42c8fc4fb9 add cal_lr.py 2023-11-14 20:58:37 +08:00
hiyouga d125ef5535 fix #1494 2023-11-14 18:07:20 +08:00
hiyouga 3743b7420b fix #1489 2023-11-14 15:27:05 +08:00
hiyouga 2d42be32c1 support eval remote dataset 2023-11-14 02:42:30 +08:00
hiyouga 88ab33254e fix dc link 2023-11-13 23:22:56 +08:00
hiyouga 35cc1e28f6 release v0.2.2, fix #1478 #1466 2023-11-13 23:09:05 +08:00
hiyouga 87390ae3b7 fix #424 2023-11-13 22:42:23 +08:00
hiyouga 442aefb925 refactor evaluation, upgrade trl to 074 2023-11-13 22:20:35 +08:00
hiyouga 528d91192a Update wechat.jpg 2023-11-12 22:34:19 +08:00
hiyouga 4bd8e3906d fix flashattn warning 2023-11-10 18:34:54 +08:00
hiyouga a0c31c68c4 add todo 2023-11-10 14:38:18 +08:00
hiyouga 3697a3dc9a refactor constants 2023-11-10 14:16:10 +08:00
hiyouga 415bca900e tiny fix 2023-11-09 17:20:49 +08:00
hoshi-hiyougaandGitHub 462730cbd7 Merge pull request #1454 from yyq/main 
Update finetuning_args.py
 2023-11-09 17:12:18 +08:00
hiyouga 0e86527d7f fix #1452 2023-11-09 16:41:32 +08:00
hiyouga b3572659f5 update readme 2023-11-09 16:00:24 +08:00
hiyouga 1db59832fd release v0.2.1 2023-11-09 15:54:16 +08:00
hiyouga 386f590209 add template, modify datasets 2023-11-09 15:53:23 +08:00
hoshi-hiyougaandGitHub 7ca32d8e69 Merge pull request #1436 from lvzii/main 
fix tokenizer config changed after pretrain
 2023-11-09 14:30:50 +08:00
hiyouga 3df90b988b support parquet format #1446 2023-11-09 14:17:40 +08:00
hiyouga 33422e1fef fix #1438 #1439 2023-11-09 13:45:10 +08:00
hiyouga 01260d9754 fix ppo train and dpo eval 2023-11-07 22:48:51 +08:00
hiyouga 11c1e1e157 fix #1422 2023-11-07 19:42:01 +08:00
hiyouga c52336d144 fix reward model loading 2023-11-07 17:20:51 +08:00
hiyouga d92f112951 fix args 2023-11-07 16:36:06 +08:00
hiyouga 17c64a0579 update info 2023-11-07 16:28:21 +08:00
hiyouga 479d0af2dc delete file 2023-11-07 16:20:12 +08:00
hiyouga 7ebd63a609 fix #1418 2023-11-07 16:17:22 +08:00
hiyouga b2a60905f3 upgrade peft, fix #1088 #1411 2023-11-07 16:13:36 +08:00
hiyouga 66a91e1fe3 update requirements 2023-11-06 19:01:21 +08:00
hiyouga de95b69282 use seed in evaluate.py 2023-11-06 18:17:51 +08:00
hiyouga e1e04cb1f1 update readme (list in alphabetical order) 2023-11-06 17:18:12 +08:00
hiyouga a7eeb8e17c update templates 2023-11-06 12:25:47 +08:00
hiyouga 2e77a5718a fix #1383 2023-11-06 11:42:23 +08:00
hiyouga d08f5e8a14 fix deepseek template 2023-11-05 13:08:46 +08:00
hiyouga 2a8a258195 support deepseek coder #1378 2023-11-05 12:51:03 +08:00
hiyouga 63ff909310 fix #1365 2023-11-05 12:21:07 +08:00
hiyouga 5227e18c44 Update wechat.jpg 2023-11-05 10:25:59 +08:00
hiyouga 05d9fc7eff tiny fix 2023-11-03 01:26:06 +08:00
hiyouga eb9d9e104a fix #1290 2023-11-03 00:44:53 +08:00
hiyouga b355f6cac9 fix bug in data loader, support dpo eval 2023-11-03 00:34:26 +08:00
hiyouga 2b5e33c338 update data readme 2023-11-03 00:15:23 +08:00
hiyouga cc8ffa10d8 update data readme (zh) 2023-11-02 23:42:49 +08:00
hiyouga a837172413 support sharegpt format, add datasets 2023-11-02 23:10:04 +08:00
hiyouga c1edb0cf1b support pagination in webui preview 2023-11-02 21:21:45 +08:00
hiyouga 34d8b2e56c fix webui 2023-11-02 18:03:14 +08:00
hiyouga 9cde5e8af6 support warning in webui 2023-11-02 17:57:04 +08:00
hiyouga f8703aac08 fix #1349 2023-11-02 17:02:44 +08:00
hiyouga dff128c7e3 fix #1356 2023-11-02 16:51:52 +08:00
hiyouga 083787dbfe fix #1325 2023-11-01 23:38:49 +08:00
hiyouga 8b912690e3 fix chat 2023-11-01 23:07:58 +08:00
hiyouga 84af10cec9 update gradio, support multiple resp in api 2023-11-01 23:02:16 +08:00
hiyouga d8cf8cfdeb fix SFT trainer 2023-10-31 21:52:52 +08:00
hiyouga f4e4a04529 fix #1316 2023-10-31 11:32:08 +08:00
hiyouga 9093cb1a2e Update wechat.jpg 2023-10-30 14:01:08 +08:00
hiyouga 640a520108 update projects 2023-10-29 22:53:47 +08:00
hiyouga 59f342e76f add projects 2023-10-29 22:07:13 +08:00
hiyouga f28a034a9b update constants 2023-10-29 13:30:20 +08:00
hiyouga 52fc24d166 fix vicuna template 2023-10-27 22:15:25 +08:00
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-hiyougaandGitHub b42a145253 Merge pull request #1252 from anvie/neftune 
add NEFTune optimization
 2023-10-22 15:59:20 +08:00
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-hiyougaandGitHub 5f83a6e72c Update README_zh.md 2023-10-16 00:28:27 +08:00
hoshi-hiyougaandGitHub 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-hiyougaandGitHub 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-hiyougaandGitHub a63a1cebb2 Merge pull request #1186 from hiyouga/dev 
Support Web UI resuming training
 2023-10-15 04:53:14 +08:00