hiyouga
|
83cee2a604
|
tiny fix
|
2023-11-16 03:27:19 +08:00 |
hiyouga
|
1817ffc86f
|
fix rlhf callback
|
2023-11-16 03:26:19 +08:00 |
hiyouga
|
856522a3df
|
fix bug in PPO training
|
2023-11-16 02:32:54 +08:00 |
hiyouga
|
35b91ea34c
|
fix import bug
|
2023-11-16 02:27:03 +08:00 |
hiyouga
|
ce78303600
|
support full-parameter PPO
|
2023-11-16 02:08:04 +08:00 |
hiyouga
|
8350bcf85d
|
add demo mode for web UI
|
2023-11-15 23:51:26 +08:00 |
hoshi-hiyouga
|
01b9f63465
|
Create CODE_OF_CONDUCT.md
|
2023-11-15 20:42:15 +08:00 |
hiyouga
|
1e19cf242a
|
update readme and constants
|
2023-11-15 18:04:37 +08:00 |
hiyouga
|
4907452d95
|
support multiple modules in freeze training #1514
|
2023-11-15 17:08:18 +08:00 |
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-hiyouga
|
462730cbd7
|
Merge pull request #1454 from yyq/main
Update finetuning_args.py
|
2023-11-09 17:12:18 +08:00 |
Yanqing
|
3684dffa14
|
Update finetuning_args.py
更新 chatglm/falcon/bloom 的 lora_target 的名称
|
2023-11-09 17:04:40 +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-hiyouga
|
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 |
lvzi
|
043c316ac8
|
fix tokenizer config changed after pretrain
Changing tokenizer's attribute at preprocessing stage will result in saving a wrong tokenizer.
for example, baichuan2
|
2023-11-08 15:50:46 +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 |