Commit Graph

2471 Commits

Author SHA1 Message Date
hiyouga
93d3b8f43f update tests 2024-11-02 12:41:44 +08:00
hoshi-hiyouga
0a55e60693 Merge pull request #5895 from hiyouga/dev
[inference] support multiple images
2024-11-01 16:52:55 +08:00
hiyouga
e824b715ad add examples 2024-11-01 08:41:54 +00:00
hiyouga
e80a481927 support multiimage inference 2024-11-01 07:25:20 +00:00
Valerio Mariani
d5b2def7c0 make base image parametric.
default `BASE_IMAGE` is nvcr.io/nvidia/pytorch:24.02-py3 for retro-compatibility
2024-10-30 21:53:32 +01:00
hoshi-hiyouga
641d0dab08 Merge pull request #5873 from hiyouga/dev
[misc] update readme
2024-10-30 17:14:44 +08:00
hiyouga
2417b70a62 update readme 2024-10-30 09:14:01 +00:00
hoshi-hiyouga
b2d4b9a7a8 Merge pull request #5871 from hiyouga/dev
[loss&ui] fix incorrect loss of vlms, add extra args to ui
2024-10-30 17:13:17 +08:00
hiyouga
30567a1487 fix incorrect loss value for vlms 2024-10-30 08:56:46 +00:00
hiyouga
0c22da4f1c tiny fix 2024-10-30 08:56:29 +00:00
hiyouga
86e5affc0d support extra args in llamaboard 2024-10-30 08:55:54 +00:00
hoshi-hiyouga
9009a467e6 Merge pull request #5581 from Kuangdd01/pixtral-patch
[WIP] Support Pixtral-12B
2024-10-29 22:29:10 +08:00
hoshi-hiyouga
bb0afda8fb fix bug 2024-10-29 22:19:04 +08:00
hoshi-hiyouga
049c554aee Update mm_plugin.py 2024-10-29 22:16:22 +08:00
hoshi-hiyouga
c3239ba6b2 Update template.py 2024-10-29 22:11:21 +08:00
hoshi-hiyouga
0baa7735f6 Update visual.py 2024-10-29 22:10:29 +08:00
hoshi-hiyouga
f745c4b28f Update collator.py 2024-10-29 22:03:42 +08:00
hoshi-hiyouga
6e212fdab5 Update hf_engine.py 2024-10-29 22:00:59 +08:00
hoshi-hiyouga
8fa20bf427 Update README_zh.md 2024-10-29 21:58:03 +08:00
hoshi-hiyouga
1b57df074a Update README.md 2024-10-29 21:57:28 +08:00
hoshi-hiyouga
4ff6e564f8 Merge pull request #5801 from NLPJCL/main
使用了 LLaMA Factory 的项目:RAG-Retrieval 使用LLaMA-Factory作为生成方法做Reranker任务的微调框架。
2024-10-29 21:20:16 +08:00
hoshi-hiyouga
08d9a03c30 Update README_zh.md 2024-10-29 21:19:17 +08:00
hoshi-hiyouga
a76478c127 Update README.md 2024-10-29 21:18:15 +08:00
hoshi-hiyouga
a7c79d8f6a Merge pull request #5857 from hiyouga/dev
[train] fix saving processor
2024-10-29 21:12:04 +08:00
hiyouga
23dbe9a099 fix #5749 2024-10-29 13:02:13 +00:00
Kingsley
67f59579d7 Merge branch 'hiyouga:main' into pixtral-patch 2024-10-29 21:01:25 +08:00
hoshi-hiyouga
935adaeed9 Merge pull request #5852 from hiyouga/dev
[misc] several important updates
2024-10-29 20:30:02 +08:00
hiyouga
51e5f96247 fix pissa 2024-10-29 12:18:45 +00:00
hiyouga
ae045c884f fix #5747 2024-10-29 10:47:04 +00:00
hiyouga
21db8ed2f4 use pre-commit 2024-10-29 09:07:46 +00:00
hiyouga
77666bd227 update requires 2024-10-29 16:10:07 +08:00
hiyouga
8723922923 update wechat 2024-10-29 15:46:10 +08:00
grok
6fcabb3349 Update README_zh.md 2024-10-23 23:50:56 +08:00
grok
7627ef0908 Update README.md
update english readme
2024-10-23 23:49:47 +08:00
grok
18a7f3ff76 Update README_zh.md 2024-10-23 23:36:14 +08:00
hoshi-hiyouga
b4c7dd3ac5 fix #5797 2024-10-23 20:49:44 +08:00
KUANGDD
c1d17b0f01 rm comment 2024-10-23 15:50:59 +08:00
KUANGDD
f5c1cdfaab rm useless code 2024-10-23 15:38:11 +08:00
KUANGDD
eb35e76d50 Merge branch 'pixtral-patch' of https://github.com/Kuangdd01/LLaMA-Factory-X into pixtral-patch 2024-10-23 15:32:50 +08:00
KUANGDD
a857184456 rm import torch 2024-10-23 15:32:33 +08:00
Kingsley
0d3106e9fa Merge branch 'hiyouga:main' into pixtral-patch 2024-10-23 15:30:03 +08:00
KUANGDD
341a79fb96 Merge branch 'pixtral-patch' of https://github.com/Kuangdd01/LLaMA-Factory-X into pixtral-patch 2024-10-23 15:28:19 +08:00
KUANGDD
9d6143e36a modify style & little change 2024-10-23 15:24:07 +08:00
hoshi-hiyouga
74a79cc059 fix test 2024-10-22 12:35:36 +08:00
hoshi-hiyouga
d155b7008c fix #5768 2024-10-22 11:06:22 +08:00
hiyouga
ed9b99b80d update wechat 2024-10-17 21:08:28 +08:00
hoshi-hiyouga
769fbb6349 Update misc.py 2024-10-17 19:48:51 +08:00
hoshi-hiyouga
93b9067dfc Update loader.py 2024-10-17 19:48:12 +08:00
hoshi-hiyouga
110e4c548d Update README_zh.md 2024-10-17 19:47:33 +08:00
hoshi-hiyouga
1fea871835 Update README.md 2024-10-17 19:46:36 +08:00