Commit Graph

2109 Commits

Author SHA1 Message Date
hiyouga
c439c959f7 add vllm_dtype arg #3387 #3717
Former-commit-id: 8fcc79e1e6
2024-06-06 02:53:27 +08:00
hiyouga
3fcb678d00 support train from scratch #4033 #4075
Former-commit-id: a12a506c3d
2024-06-06 02:43:19 +08:00
hiyouga
cafbb79d3a support image input in api #3971 #4061
Former-commit-id: 946f601136
2024-06-06 02:29:55 +08:00
hiyouga
00b3fb4d14 update train hparams
Former-commit-id: dc4a00dd63
2024-06-06 01:49:20 +08:00
hiyouga
8f3b8ade45 fix setup
Former-commit-id: 4dc0632145
2024-06-06 01:39:02 +08:00
hiyouga
0398338a0f add llamafactory-cli env
Former-commit-id: d4908d5708
2024-06-06 01:28:14 +08:00
hiyouga
a16786d8ba fix #4090
Former-commit-id: 67fe822324
2024-06-06 00:50:32 +08:00
MengqingCao
71b9b87d88 modify export_device option
Former-commit-id: 2c03052662
2024-06-05 09:37:36 +00:00
hiyouga
ecd06d0110 fix #4079
Former-commit-id: 83a005e3d4
2024-06-05 16:56:54 +08:00
hiyouga
b097f04a79 update readme
Former-commit-id: eef1e542a9
2024-06-05 16:32:32 +08:00
MengqingCao
55815ab1ff fix #4077
Former-commit-id: 90ed3cae92
2024-06-05 08:03:30 +00:00
hiyouga
94c37490d1 support glm-4
Former-commit-id: f48f5e646e
2024-06-05 15:16:38 +08:00
MengqingCao
15f6ab73a5 add npu for model export
Former-commit-id: 07045c876a
2024-06-05 07:06:40 +00:00
faddddeout
a2931b813b add throughput entry to log
Former-commit-id: b2f0459542
2024-06-04 11:04:29 +00:00
hiyouga
51e3229528 update wechat
Former-commit-id: 82a565362c
2024-06-04 15:52:56 +08:00
hzhaoy
4721d0b8ff add: support selecting saved configuration files and loading training parameters
Former-commit-id: b27c4cfcb3
2024-06-04 10:33:43 +08:00
hiyouga
0eff6a66d5 tiny fix
Former-commit-id: 5a13b3baa6
2024-06-04 00:31:10 +08:00
hiyouga
88745c9bb5 fix #3873
Former-commit-id: 91611d68c4
2024-06-04 00:21:50 +08:00
hiyouga
8ecf606230 fix #3992
Former-commit-id: a18acf2abe
2024-06-04 00:17:36 +08:00
hiyouga
b12d4beb8a fix abort in webui DDP mode
Former-commit-id: 2187518762
2024-06-04 00:10:24 +08:00
hoshi-hiyouga
326f180397 Merge pull request #3987 from injet-zhou/main
Fix cann't interrupt training when using multi GPUs in webui

Former-commit-id: ae18e1e251
2024-06-04 00:04:07 +08:00
hiyouga
e2920aa925 fix #4043
Former-commit-id: 79784ebeb6
2024-06-03 23:30:37 +08:00
hiyouga
6f7b6ae0c3 remove gc warnings in DPO&KTO
Former-commit-id: f9a206509e
2024-06-03 22:53:54 +08:00
hoshi-hiyouga
b2c224de69 Merge pull request #4045 from enji-zhou/feature/add_kto
fix KTO Trainer Sampler

Former-commit-id: 30a538e2db
2024-06-03 22:09:25 +08:00
hoshi-hiyouga
5d96cf146e Update trainer.py
Former-commit-id: 24499f40dc
2024-06-03 22:08:38 +08:00
enji.zhou
e58aca0602 fix KTO Trainer Sampler
Former-commit-id: 34a2c5087a
2024-06-03 21:32:38 +08:00
hoshi-hiyouga
f6f1c4eacb Merge pull request #4006 from Uminosachi/scheduler-kwargs
Set scheduler_specific_kwargs to get_scheduler

Former-commit-id: 0f01500b68
2024-06-03 19:27:53 +08:00
hiyouga
a187068e7c update placeholder in issue template
Former-commit-id: 88681d3357
2024-06-03 19:24:10 +08:00
hoshi-hiyouga
cdfd2ad4b1 Merge pull request #4011 from statelesshz/issue-template
Update bug-report.yml

Former-commit-id: d359dd2de4
2024-06-03 19:20:43 +08:00
hiyouga
e4ce59243b fix #4005 #4013
Former-commit-id: eed33862bc
2024-06-03 19:12:29 +08:00
hoshi-hiyouga
eaab09fccb Merge pull request #4007 from xu-song/patch-3
Update model_args.py

Former-commit-id: 1539c72b94
2024-06-03 18:54:37 +08:00
hiyouga
d0ceb1b091 fix #4022
Former-commit-id: 24e1c0e2ee
2024-06-03 18:38:36 +08:00
hiyouga
af7748139a bump versions
transformers 4.37.2->4.41.2
datasets 2.14.3->2.16.0
accelerate 0.27.2->0.30.1
peft 0.10.0->0.11.1
trl 0.8.1->0.8.6


Former-commit-id: 876bc92865
2024-06-03 18:29:38 +08:00
hiyouga
64d24842fe fix data loader hint
Former-commit-id: 49b1e88e3d
2024-06-03 18:28:27 +08:00
ylfeng
62d55b71a3 remove empty line
Former-commit-id: b47e317447
2024-05-31 21:43:08 +08:00
ylfeng
0feb2ad35c fix eos
Former-commit-id: 84aee57901
2024-05-31 21:40:41 +08:00
ylfeng
8350e508d3 supervised packing with greedy knapsack algorithm
Former-commit-id: f9db439cb7
2024-05-31 15:33:54 +08:00
Xu Song
abe33220bf Update model_args.py
Former-commit-id: dade2f083d
2024-05-31 14:35:48 +08:00
statelesshz
6a6f07053d Update bug-report.yml
Former-commit-id: f78e21f341
2024-05-31 13:18:18 +08:00
Uminosachi
0de4e1e9e2 Set scheduler_specific_kwargs to get_scheduler
Former-commit-id: 14e97dc119
2024-05-31 13:45:39 +09:00
hiyouga
72ebcb9a04 update readme
Former-commit-id: c4f50865ad
2024-05-30 16:40:17 +08:00
faddddeout
64976e426c fix cann't interrupt training when using multi GPUs in webui
Former-commit-id: b13d03946e
2024-05-30 08:39:21 +00:00
hoshi-hiyouga
e24276cab6 Update wechat.jpg
Former-commit-id: 2f38c1f5fd
2024-05-30 12:48:47 +08:00
hiyouga
107e39f2de fix #3837
Former-commit-id: 3404e8f302
2024-05-30 00:52:26 +08:00
hoshi-hiyouga
9b6bdf9449 Merge pull request #3829 from seanzhang-zhichen/add_dataset_sample_num
Add dataset sample num

Former-commit-id: 483eb47e5d
2024-05-30 00:25:45 +08:00
hoshi-hiyouga
7b83c550ab Update loader.py
Former-commit-id: ca5dd7c6c1
2024-05-30 00:20:20 +08:00
hoshi-hiyouga
9fc713da89 Update loader.py
Former-commit-id: f9a88b89ca
2024-05-30 00:17:21 +08:00
hoshi-hiyouga
c0f11a280e Update loader.py
Former-commit-id: b55fb611c5
2024-05-30 00:12:12 +08:00
hoshi-hiyouga
69a51cacb1 Update parser.py
Former-commit-id: 51dd454337
2024-05-30 00:05:20 +08:00
hoshi-hiyouga
21e7979837 Update README_zh.md
Former-commit-id: c8ae7e0e65
2024-05-30 00:04:47 +08:00