hoshi-hiyouga
|
d72f123851
|
Merge pull request #1553 from hannlp/hans
Change the default argument settings for PPO training
Former-commit-id: 48211e3799
|
2023-11-20 20:32:55 +08:00 |
|
hiyouga
|
a7b1632ace
|
fix value head model resuming
Former-commit-id: 2a36fd5064
|
2023-11-20 19:01:37 +08:00 |
|
hiyouga
|
682d81caa9
|
fix #1567
Former-commit-id: 99a3f06377
|
2023-11-20 18:46:36 +08:00 |
|
hiyouga
|
32545bd6d9
|
better data streaming
Former-commit-id: 00baaa990e
|
2023-11-19 23:32:47 +08:00 |
|
hiyouga
|
d1e03512f4
|
fix model card network issue
Former-commit-id: 211b2db5a8
|
2023-11-19 23:03:19 +08:00 |
|
hiyouga
|
8d82d7e994
|
fix Mistral template
https://github.com/lm-sys/FastChat/pull/2547
Former-commit-id: bfb9433165
|
2023-11-19 16:29:30 +08:00 |
|
hiyouga
|
a53afb27eb
|
fix #1263
Former-commit-id: 065bfaeed4
|
2023-11-19 16:05:18 +08:00 |
|
hiyouga
|
48d6d925f7
|
fix #1558
Former-commit-id: 1740131d63
|
2023-11-19 14:15:47 +08:00 |
|
hiyouga
|
112108d564
|
fix evaluator and cached_file in 4.31.0
Former-commit-id: ff6056405d
|
2023-11-18 19:39:23 +08:00 |
|
hiyouga
|
0d98d1a28c
|
fix quantization
Former-commit-id: ccb0f58e22
|
2023-11-17 22:21:29 +08:00 |
|
hiyouga
|
f9df6c17ed
|
fix #1550
Former-commit-id: 1bbc1be95e
|
2023-11-17 17:23:13 +08:00 |
|
Yuchen Han
|
a419122179
|
Update workflow.py
Former-commit-id: eeb5249d0b
|
2023-11-17 00:16:27 -08:00 |
|
Yuchen Han
|
ec910a87c0
|
Update finetuning_args.py
Former-commit-id: b24635d22b
|
2023-11-17 00:15:51 -08:00 |
|
hiyouga
|
d3c4881ccb
|
fix packages
Former-commit-id: 999bc0ed93
|
2023-11-17 16:11:48 +08:00 |
|
Shaowen Wang
|
4ea3144554
|
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: 397e948984
|
2023-11-16 20:12:35 -06:00 |
|
hiyouga
|
5de45bf989
|
fix chatglm template
Former-commit-id: ed9f7705ef
|
2023-11-16 22:54:15 +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
|
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 |
|
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
|
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
|
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
|
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 |
|
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
|
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 |
|