Commit Graph

2703 Commits

Author SHA1 Message Date
hiyouga
4a6cb33f0c Update bug-report.yml
Former-commit-id: 438c374567
2023-11-16 19:37:35 +08:00
hiyouga
1fd8f1eb72 add issue template
Former-commit-id: 9e0bfcfc14
2023-11-16 19:35:30 +08:00
hoshi-hiyouga
39735b5750 Update issue templates
Former-commit-id: dea176f88e
2023-11-16 18:56:30 +08:00
hiyouga
8454e02313 fix web ui demo
Former-commit-id: 10ce87e088
2023-11-16 18:41:55 +08:00
hiyouga
be0fb659d2 fix web ui demo
Former-commit-id: 1c80e9a09e
2023-11-16 17:12:23 +08:00
hiyouga
11af6c1e39 release v0.3.0
Former-commit-id: c4facc03af
2023-11-16 16:00:11 +08:00
hiyouga
763a9305d0 update readme
Former-commit-id: 72e6699547
2023-11-16 15:58:37 +08:00
hoshi-hiyouga
550293badc Merge #1525 from hiyouga/dev, fix #224 #336 #931 #936 #1011
Refactor llmtuner, support full-parameter RLHF

Former-commit-id: f04bc2a428
2023-11-16 15:47:13 +08:00
hiyouga
11de514cc6 fix css
Former-commit-id: 08f3c11429
2023-11-16 15:45:38 +08:00
hiyouga
3f53155a90 fix bug in web ui
Former-commit-id: 6efa38be46
2023-11-16 15:21:24 +08:00
hiyouga
e4f97615f0 update ppo and demo in webui
Former-commit-id: 7537dd434f
2023-11-16 14:55:26 +08:00
hiyouga
0ed0b8f9c5 fix bug in freeze tuning
Former-commit-id: ff52b1779c
2023-11-16 14:25:11 +08:00
hiyouga
627212e48b tiny fix
Former-commit-id: 83cee2a604
2023-11-16 03:27:19 +08:00
hiyouga
678052a7ef fix rlhf callback
Former-commit-id: 1817ffc86f
2023-11-16 03:26:19 +08:00
hiyouga
b71da932eb fix bug in PPO training
Former-commit-id: 856522a3df
2023-11-16 02:32:54 +08:00
hiyouga
eb5a852dd5 fix import bug
Former-commit-id: 35b91ea34c
2023-11-16 02:27:03 +08:00
hiyouga
f441932bd1 support full-parameter PPO
Former-commit-id: ce78303600
2023-11-16 02:08:04 +08:00
hiyouga
0c1fab84f1 add demo mode for web UI
Former-commit-id: 8350bcf85d
2023-11-15 23:51:26 +08:00
hoshi-hiyouga
2ec5c734f3 Create CODE_OF_CONDUCT.md
Former-commit-id: 01b9f63465
2023-11-15 20:42:15 +08:00
hiyouga
3e0b76650a update readme and constants
Former-commit-id: 1e19cf242a
2023-11-15 18:04:37 +08:00
hiyouga
e30290444a support multiple modules in freeze training #1514
Former-commit-id: 4907452d95
2023-11-15 17:08:18 +08:00
hiyouga
4a0be64ae6 fix imports
Former-commit-id: bbbce1f516
2023-11-15 16:47:45 +08:00
hiyouga
06a4820836 disentangle model from tuner and rename modules
Former-commit-id: 4736344eb1
2023-11-15 16:29:09 +08:00
hiyouga
8ee48a9c9e fix #1507
Former-commit-id: 2f02f688e1
2023-11-15 16:22:32 +08:00
hiyouga
2ba88c6b08 Update cal_lr.py
Former-commit-id: 829e879e04
2023-11-14 21:14:42 +08:00
hiyouga
426c2fc340 Update cal_lr.py
Former-commit-id: 5619e76dc5
2023-11-14 21:13:01 +08:00
hiyouga
b45fb2b3da Update cal_lr.py
Former-commit-id: fcb2daf7f3
2023-11-14 21:09:30 +08:00
hiyouga
fffb8ea764 add cal_lr.py
Former-commit-id: 42c8fc4fb9
2023-11-14 20:58:37 +08:00
hiyouga
8387f3011c fix #1494
Former-commit-id: d125ef5535
2023-11-14 18:07:20 +08:00
hiyouga
9176b55fe6 fix #1489
Former-commit-id: 3743b7420b
2023-11-14 15:27:05 +08:00
hiyouga
5c4ddebde5 support eval remote dataset
Former-commit-id: 2d42be32c1
2023-11-14 02:42:30 +08:00
hiyouga
42bb8b6400 fix dc link
Former-commit-id: 88ab33254e
2023-11-13 23:22:56 +08:00
hiyouga
4a767e5593 release v0.2.2, fix #1478 #1466
Former-commit-id: 35cc1e28f6
2023-11-13 23:09:05 +08:00
hiyouga
37db26800c fix #424
Former-commit-id: 87390ae3b7
2023-11-13 22:42:23 +08:00
hiyouga
125587b187 refactor evaluation, upgrade trl to 074
Former-commit-id: 442aefb925
2023-11-13 22:20:35 +08:00
hiyouga
d83cf3cbc6 Update wechat.jpg
Former-commit-id: 528d91192a
2023-11-12 22:34:19 +08:00
hiyouga
982e0e79c2 fix flashattn warning
Former-commit-id: 4bd8e3906d
2023-11-10 18:34:54 +08:00
hiyouga
55e097aaac add todo
Former-commit-id: a0c31c68c4
2023-11-10 14:38:18 +08:00
hiyouga
0fbaa42752 refactor constants
Former-commit-id: 3697a3dc9a
2023-11-10 14:16:10 +08:00
hiyouga
6ee32cf71c tiny fix
Former-commit-id: 415bca900e
2023-11-09 17:20:49 +08:00
hoshi-hiyouga
9b98790fb3 Merge pull request #1454 from yyq/main
Update finetuning_args.py

Former-commit-id: 462730cbd7
2023-11-09 17:12:18 +08:00
Yanqing
fc05fd52cf Update finetuning_args.py
更新 chatglm/falcon/bloom 的 lora_target 的名称

Former-commit-id: 3684dffa14
2023-11-09 17:04:40 +08:00
hiyouga
4dbb52750f fix #1452
Former-commit-id: 0e86527d7f
2023-11-09 16:41:32 +08:00
hiyouga
164559d01d update readme
Former-commit-id: b3572659f5
2023-11-09 16:00:24 +08:00
hiyouga
c5b202d5c6 release v0.2.1
Former-commit-id: 1db59832fd
2023-11-09 15:54:16 +08:00
hiyouga
38755bced7 add template, modify datasets
Former-commit-id: 386f590209
2023-11-09 15:53:23 +08:00
hoshi-hiyouga
28a9176784 Merge pull request #1436 from lvzii/main
fix tokenizer config changed after pretrain

Former-commit-id: 7ca32d8e69
2023-11-09 14:30:50 +08:00
hiyouga
f9ebc718d0 support parquet format #1446
Former-commit-id: 3df90b988b
2023-11-09 14:17:40 +08:00
hiyouga
b9f42172dd fix #1438 #1439
Former-commit-id: 33422e1fef
2023-11-09 13:45:10 +08:00
lvzi
13eb365eb7 fix tokenizer config changed after pretrain
Changing tokenizer's attribute at preprocessing stage will result in saving a wrong tokenizer.
for example, baichuan2

Former-commit-id: 043c316ac8
2023-11-08 15:50:46 +08:00