421d4de604
Improve："CUDA_VISIBLE_DEVICES" read from the env
2023-12-01 11:35:02 +08:00
9468ee9012
Update dataset_info.json
...
Added the Nectar dataset already preprocessed and divided in sft and rl to which I added a preprompt to each instruction since it has been seen that this increase instruction following
2023-11-30 16:21:34 +01:00
40dfcbc3d4
improve get_current_device
2023-11-30 22:40:35 +08:00
327d7f7efe
fix #1597
2023-11-30 21:47:06 +08:00
1585962eb7
fix #1668
2023-11-30 21:02:00 +08:00
a38dbf55e3
fix #1682
2023-11-30 20:03:32 +08:00
509abe8864
add models
2023-11-30 19:16:13 +08:00
fb2204c183
fix
2023-11-29 21:43:58 +08:00
d38a2e7341
support ms
2023-11-29 20:36:55 +08:00
9d38e5687d
add gpu requirement #1657
2023-11-29 12:05:03 +08:00
77d1b14fc2
fix #1658
2023-11-28 20:57:24 +08:00
475a3fa0f4
fix #1659
2023-11-28 20:52:28 +08:00
c2d4300ac4
Update wechat.jpg
2023-11-28 17:27:23 +08:00
859a6ea942
support export size setting
2023-11-26 18:34:09 +08:00
ff1c289229
support Yi-34B-Chat models
2023-11-23 19:31:49 +08:00
5085b00a1d
update readme
2023-11-21 13:15:46 +08:00
35c2da3eba
set version
2023-11-20 22:57:44 +08:00
9ea9380145
support GPTQ tuning #729 #1481 #1545 , fix chatglm template #1453 #1480 #1569
2023-11-20 22:52:11 +08:00
5021062493
update ppo trainer
2023-11-20 21:39:15 +08:00
48211e3799
Merge pull request #1553 from hannlp/hans
...
Change the default argument settings for PPO training
2023-11-20 20:32:55 +08:00
2a36fd5064
fix value head model resuming
2023-11-20 19:01:37 +08:00
99a3f06377
fix #1567
2023-11-20 18:46:36 +08:00
00baaa990e
better data streaming
2023-11-19 23:32:47 +08:00
211b2db5a8
fix model card network issue
2023-11-19 23:03:19 +08:00
bfb9433165
fix Mistral template
...
https://github.com/lm-sys/FastChat/pull/2547
2023-11-19 16:29:30 +08:00
065bfaeed4
fix #1263
2023-11-19 16:05:18 +08:00
1740131d63
fix #1558
2023-11-19 14:15:47 +08:00
ff6056405d
fix evaluator and cached_file in 4.31.0
2023-11-18 19:39:23 +08:00
a2019c8b61
update benchmark
2023-11-18 11:30:01 +08:00
90212280d6
update readme
2023-11-18 11:15:56 +08:00
329134f58c
add benchmark
2023-11-18 11:09:52 +08:00
7b1aa6f63c
update dataset
2023-11-17 23:19:12 +08:00
ccb0f58e22
fix quantization
2023-11-17 22:21:29 +08:00
1bbc1be95e
fix #1550
2023-11-17 17:23:13 +08:00
7cab47b822
Update README_zh.md
2023-11-17 00:18:07 -08:00
c9b499fa7e
Update README.md
2023-11-17 00:17:36 -08:00
eeb5249d0b
Update workflow.py
2023-11-17 00:16:27 -08:00
b24635d22b
Update finetuning_args.py
2023-11-17 00:15:51 -08:00
999bc0ed93
fix packages
2023-11-17 16:11:48 +08:00
7f9770b2c6
Merge #1544 from Outsider565/main, fix #1548
...
Fix: Change rouge-chinese package name to rouge_chinese
2023-11-17 16:09:42 +08:00
397e948984
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
2023-11-16 20:12:35 -06:00
ed9f7705ef
fix chatglm template
2023-11-16 22:54:15 +08:00
438c374567
Update bug-report.yml
2023-11-16 19:37:35 +08:00
9e0bfcfc14
add issue template
2023-11-16 19:35:30 +08:00
dea176f88e
Update issue templates
2023-11-16 18:56:30 +08:00
10ce87e088
fix web ui demo
2023-11-16 18:41:55 +08:00
1c80e9a09e
fix web ui demo
2023-11-16 17:12:23 +08:00
c4facc03af
release v0.3.0
2023-11-16 16:00:11 +08:00
72e6699547
update readme
2023-11-16 15:58:37 +08:00
f04bc2a428
Merge #1525 from hiyouga/dev, fix #224 #336 #931 #936 #1011
...
Refactor llmtuner, support full-parameter RLHF
2023-11-16 15:47:13 +08:00
samge