hoshi-hiyouga
b00b290c07
[version] support transformers 449 ( #6982 )
...
* support transformers 449
* fix mm plugin
2025-02-18 17:05:40 +08:00
marko1616
b7fd1e9c00
[trainer] fix llama3.2 vision kto train ( #6904 )
2025-02-12 19:09:14 +08:00
Zhangchi Feng
764627645a
[da'ta] fix minicpmv plugin ( #6890 )
...
* fix template name
* tiny fix
* support minicpm-o-2.6
* support inference of minicpmv
* update readme
* support dpo of minicpmv
* update init audio
* update init audio
* [model]fix image process in minicpmo
* fix no mm inputs
2025-02-11 13:30:44 +08:00
hoshi-hiyouga
b68199db27
[data] fix mllama collator ( #6874 )
2025-02-09 22:42:25 +08:00
Zhangchi Feng
24c7842948
[model] support audio ( #6701 )
...
* support qwen2_audio
* improve code
* lint
* fix
* fix
* fix
---------
Co-authored-by: hiyouga <hiyouga@buaa.edu.cn >
2025-02-05 04:59:09 +08:00
hoshi-hiyouga
999c7c8fe0
[model] add qwen2.5 vl models ( #6779 )
2025-01-31 03:00:29 +08:00
Zhangchi Feng
027942789b
[data] Fix minicpmv/o dpo training ( #6657 )
...
* fix template name
* tiny fix
* support minicpm-o-2.6
* support inference of minicpmv
* update readme
* support dpo of minicpmv
2025-01-15 17:30:37 +08:00
Zhangchi Feng
c3fda5046d
Support new features of MiniCPM-V ( #6626 )
...
* fix template name
* tiny fix
* support minicpm-o-2.6
2025-01-14 00:26:19 +08:00
hoshi-hiyouga
e3e2c8c689
[inference] fix stop token for object detection ( #6624 )
...
* fix stop token
* update minicpm data pipeline
* fix npu qlora examples
2025-01-13 21:34:20 +08:00
fzc8578
0cc7260a93
fix style
2025-01-13 14:19:38 +08:00
fzc8578
cfaa8e4890
fix system prompt and tests
2025-01-13 14:18:06 +08:00
fzc8578
7b44f3127e
fix format
2025-01-11 01:27:40 +08:00
fzc8578
a650e114e9
add some
2025-01-11 01:10:24 +08:00
fzc8578
291384dea8
adapt to new mllm_param
2025-01-11 00:16:34 +08:00
fzc8578
771cc80294
add some
2025-01-10 23:29:06 +08:00
fzc8578
ae1f528df3
add some
2025-01-10 21:25:32 +08:00
fzc8578
2ee8ba2f39
fix some
2025-01-10 20:27:06 +08:00
fzc8578
096a6cb67a
add some
2025-01-10 20:01:22 +08:00
fzc8578
79c2d7090c
add some
2025-01-04 11:11:15 +08:00
hiyouga
6f5bb3b8e5
fix #6482
2024-12-30 06:03:07 +00:00
hiyouga
2719867982
fix #6448
2024-12-27 16:54:39 +00:00
hiyouga
142191e466
fix #6348
2024-12-17 10:06:46 +00:00
hiyouga
2811814fc4
fix mrope
2024-12-12 15:08:17 +00:00
hiyouga
eb3e147d19
fix scripts
2024-12-05 03:47:32 +00:00
hiyouga
dbb9e5b70e
fix vlm zero3 training
2024-12-04 09:40:39 +00:00
hiyouga
598c22e43f
fix mllama cross_mask
2024-11-26 15:56:58 +00:00
hiyouga
446441fdb0
fix inputs
2024-11-23 18:26:02 +00:00
hoshi-hiyouga
f745c4b28f
Update collator.py
2024-10-29 22:03:42 +08:00
Kingsley
67f59579d7
Merge branch 'hiyouga:main' into pixtral-patch
2024-10-29 21:01:25 +08:00
hiyouga
21db8ed2f4
use pre-commit
2024-10-29 09:07:46 +00:00
KUANGDD
9d6143e36a
modify style & little change
2024-10-23 15:24:07 +08:00
hiyouga
76f2e59504
tiny fix
2024-09-05 23:41:16 +08:00
hiyouga
8cafc7b055
video datasets
2024-09-05 02:04:17 +08:00
hiyouga
47ea97fb1b
lazy image load
2024-09-04 02:27:08 +08:00
hiyouga
8e49940746
add rlhf-v dataset
2024-09-01 22:57:41 +08:00
hiyouga
64cb947c60
fix bug
2024-09-01 21:07:49 +08:00
hiyouga
9967ccb3ae
fix mixed mm inputs and rlhf-v
2024-09-01 20:52:47 +08:00
hiyouga
bee1bd43b9
tiny fix
2024-08-30 03:21:50 +08:00
hiyouga
3382317e32
refactor mm training
2024-08-30 02:14:31 +08:00
simonJJJ
aeb85f200b
initial-commit
2024-08-28 16:51:35 +08:00
hiyouga
2f6af73da2
fix gemma2 attention
2024-07-13 23:33:45 +08:00
hzhaoy
738df47748
tiny fix
2024-07-04 10:20:28 +08:00
hiyouga
6fd6aa4530
fix packing for eager/sdpa attn
2024-07-04 01:52:43 +08:00
hiyouga
cce7083024
update packing
2024-07-04 01:10:55 +08:00
hiyouga
575a02a23d
update hparams
2024-07-03 23:18:58 +08:00
hiyouga
d87108daa6
add license
2024-06-15 17:54:33 +08:00
hiyouga
3a023bca2a
refactor data preprocessing, fix mllm rlhf
2024-05-24 04:08:25 +08:00
hiyouga
c450ee87a3
improve KTO impl., replace datasets
2024-05-18 03:44:56 +08:00
enji.zhou
db1d5a4f51
add kto
2024-05-17 13:09:17 +08:00
hiyouga
308edbc426
rename package
2024-05-16 18:39:08 +08:00