BUAADreamer
|
119af92620
|
Merge branch 'hiyouga:main' into main
Former-commit-id: 047a06a1e5
|
2024-05-24 09:50:00 +08:00 |
|
hiyouga
|
3e729798df
|
refactor data preprocessing, fix mllm rlhf
Former-commit-id: 3a023bca2a
|
2024-05-24 04:08:25 +08:00 |
|
hoshi-hiyouga
|
77b5779746
|
Merge pull request #3876 from dongdongqiang2018/main
added adapted to 910B image
Former-commit-id: a506f3628b
|
2024-05-24 01:54:30 +08:00 |
|
hiyouga
|
d3490aceb7
|
fix paligemma sft
requires transformers>=4.41.1
Former-commit-id: de0e67aff1
|
2024-05-24 00:23:40 +08:00 |
|
hiyouga
|
6d8ef03741
|
fix oom issues in export
Former-commit-id: 67ebc7b388
|
2024-05-23 23:32:45 +08:00 |
|
donggang
|
3f52df0ca9
|
adapted to 910B image
Former-commit-id: 2f68a71fc0
|
2024-05-23 09:48:22 +00:00 |
|
BUAADreamer
|
d8a27e40e2
|
Merge branch 'hiyouga:main' into main
Former-commit-id: 8d53ec2b5f
|
2024-05-21 22:18:20 +08:00 |
|
hiyouga
|
4ddc1c9c16
|
fix paligemma sft
Former-commit-id: 7134fb02bb
|
2024-05-21 20:03:09 +08:00 |
|
hiyouga
|
a8480baa11
|
Update README_zh.md
Former-commit-id: 4d647ddba5
|
2024-05-21 18:30:59 +08:00 |
|
hiyouga
|
eabaf0def8
|
update wechat
Former-commit-id: 2670f6fb3d
|
2024-05-21 18:22:32 +08:00 |
|
hiyouga
|
11f79ea20e
|
fix #3847
Former-commit-id: 335501e228
|
2024-05-21 17:53:06 +08:00 |
|
hiyouga
|
c03be5fe63
|
Update wechat.jpg
Former-commit-id: 789e73b0f4
|
2024-05-21 17:09:43 +08:00 |
|
BUAADreamer
|
071d674065
|
support pretraining of llava
Former-commit-id: 29a6d5bdb8
|
2024-05-21 08:57:14 +08:00 |
|
hiyouga
|
cce3892f91
|
support paligemma
Former-commit-id: 2a67457e39
|
2024-05-21 00:01:22 +08:00 |
|
hiyouga
|
a935c5105d
|
fix paligemma data preprocess
Former-commit-id: e55c85ac72
|
2024-05-20 23:51:32 +08:00 |
|
hiyouga
|
446c681b58
|
fix paligemma inference
Former-commit-id: 542229abb3
|
2024-05-20 23:36:43 +08:00 |
|
hiyouga
|
7f6c37c68e
|
fix #3818
Former-commit-id: 7262679666
|
2024-05-20 21:43:19 +08:00 |
|
hiyouga
|
5351e3945b
|
add kto to webui
Former-commit-id: 9b0f4d7602
|
2024-05-20 21:20:25 +08:00 |
|
hiyouga
|
864da49139
|
fix chat engines
do not use pop(key, default) since api assigns None to dict values
Former-commit-id: d52fae2fa8
|
2024-05-20 00:36:43 +08:00 |
|
hoshi-hiyouga
|
6955042c10
|
Merge pull request #3812 from ycjcl868/feat/chat-support-system-prompt
feat: cli chat support system_message
Former-commit-id: aa0bca49e9
|
2024-05-20 00:31:32 +08:00 |
|
hoshi-hiyouga
|
02fdf903e8
|
Update vllm_engine.py
Former-commit-id: a0e8d3d159
|
2024-05-20 00:31:04 +08:00 |
|
hoshi-hiyouga
|
30b2ec7025
|
Update hf_engine.py
Former-commit-id: a943a1034b
|
2024-05-20 00:30:45 +08:00 |
|
hoshi-hiyouga
|
a710d97748
|
Update generating_args.py
Former-commit-id: a1fa7aa63b
|
2024-05-20 00:29:31 +08:00 |
|
hoshi-hiyouga
|
b293939c24
|
Update chat_model.py
Former-commit-id: 896c656185
|
2024-05-20 00:29:12 +08:00 |
|
hiyouga
|
0e57bb201c
|
fix jinja template
Former-commit-id: 10573e1639
|
2024-05-19 23:38:30 +08:00 |
|
ycjcl868
|
b28f9ecaa0
|
feat: cli chat support system_message
Former-commit-id: a08ba254c8
|
2024-05-19 23:17:46 +08:00 |
|
hiyouga
|
8d4a5ebf6e
|
fix zero2 high ram usage
Former-commit-id: 31a0564d4f
|
2024-05-19 21:53:54 +08:00 |
|
hiyouga
|
5f48c282d3
|
fix hf gen args
Former-commit-id: 70214b71b1
|
2024-05-19 19:39:32 +08:00 |
|
hiyouga
|
32a65e89e5
|
fix envs
Former-commit-id: 8ee8ac6eba
|
2024-05-19 18:27:18 +08:00 |
|
hiyouga
|
df4aec7e72
|
fix #3807
Former-commit-id: 1ebc890a5f
|
2024-05-19 17:07:57 +08:00 |
|
hiyouga
|
62ddab4b3a
|
update readme
Former-commit-id: 2bec28e328
|
2024-05-18 23:09:03 +08:00 |
|
hiyouga
|
02f716907e
|
safe output path in webui
Former-commit-id: 3c2a992caa
|
2024-05-18 22:42:28 +08:00 |
|
hiyouga
|
7130efff54
|
fix jetmoe z3 block
Former-commit-id: d43822fcc2
|
2024-05-18 22:28:45 +08:00 |
|
hiyouga
|
519d2511ae
|
improve data process logger
Former-commit-id: a851056229
|
2024-05-18 22:02:42 +08:00 |
|
hiyouga
|
c53e626c9a
|
update data readme
Former-commit-id: ca48f90f1e
|
2024-05-18 21:37:38 +08:00 |
|
hiyouga
|
68c07d3e1e
|
update data readme
Former-commit-id: 18cbf8561d
|
2024-05-18 21:15:20 +08:00 |
|
hiyouga
|
1e867c0fa0
|
fix #3803
Former-commit-id: 0edc16769f
|
2024-05-18 16:13:14 +08:00 |
|
hoshi-hiyouga
|
9fba1bb649
|
Merge pull request #3799 from hiyouga/dev
improve KTO impl, replace datasets
Former-commit-id: 73d4a8e655
|
2024-05-18 03:49:13 +08:00 |
|
hiyouga
|
13d7b48efe
|
improve KTO impl., replace datasets
Former-commit-id: c450ee87a3
|
2024-05-18 03:44:56 +08:00 |
|
hoshi-hiyouga
|
97469892c3
|
Merge pull request #3785 from enji-zhou/feature/add_kto
add kto
Former-commit-id: 33a354548e
|
2024-05-18 03:07:18 +08:00 |
|
hoshi-hiyouga
|
2d1583faba
|
Merge pull request #3794 from jue-jue-zi/main
feat: pass the `max_lora_rank` parameter to vLLM backend
Former-commit-id: d7ff49f245
|
2024-05-17 16:17:30 +08:00 |
|
hoshi-hiyouga
|
e4a2accf4a
|
Update model_args.py
Former-commit-id: 9646727453
|
2024-05-17 16:16:41 +08:00 |
|
juejuezi
|
20326affde
|
feat: pass the max_lora_rank parameter to vLLM backend
Former-commit-id: b20d62ba3c
|
2024-05-17 16:07:39 +08:00 |
|
hiyouga
|
9af3dce3c8
|
add deepseek v2 lite model
Former-commit-id: 8af9817605
|
2024-05-17 13:25:36 +08:00 |
|
enji.zhou
|
03956053b8
|
add kto
Former-commit-id: db1d5a4f51
|
2024-05-17 13:09:17 +08:00 |
|
hiyouga
|
1bbbcb5895
|
Update wechat.jpg
Former-commit-id: 84415492bf
|
2024-05-17 12:18:03 +08:00 |
|
hiyouga
|
947f0e9964
|
update badam example #3764
Former-commit-id: e5bba7cf1b
|
2024-05-17 02:21:10 +08:00 |
|
hiyouga
|
780a1f5a4e
|
better dtype handle in loading
Former-commit-id: d9f190ff1e
|
2024-05-17 02:14:56 +08:00 |
|
hiyouga
|
dfff5119b4
|
update examples
Former-commit-id: ddec9e1b84
|
2024-05-17 01:02:00 +08:00 |
|
hiyouga
|
f4bf49e891
|
enable inbrowser in webui
Former-commit-id: 694a05fd04
|
2024-05-17 00:08:56 +08:00 |
|