143 Commits

Author SHA1 Message Date
Kingsley
fef86fa7fe
[data] fix qwen3omni audio length calculation (#9467) 2025-11-12 10:37:15 +08:00
Yaowei Zheng
3ae15da9c0
[misc] lint code (#9395) 2025-11-03 22:08:59 +08:00
魅影
215580c77d
[data] fix mm pluigin for qwen omni video training (#9388)
Co-authored-by: frozenleaves <frozen@Mac.local>
2025-11-03 11:44:27 +08:00
Xiaosu Zhu
129e918106
[data] Fix Qwen3VL plugin (#9297)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Yaowei Zheng <hiyouga@buaa.edu.cn>
Co-authored-by: kingsley <kingsleydodonow@gmail.com>
2025-10-26 16:07:04 +08:00
Yaowei Zheng
6ffebe5ff7 [data] fix qwen omni plugin (#9204)
Co-authored-by: kingsley <kingsleydodonow@gmail.com>
2025-09-28 01:02:29 +08:00
xvxuopop
0761a4448f [model] add qwen3-vl/qwen3-omni (#9196)
Co-authored-by: kingsley <kingsleydodonow@gmail.com>
2025-09-27 01:21:47 +08:00
Yaowei Zheng
80fe3a172d [model] add dots ocr (#9176) 2025-09-21 23:34:19 +08:00
Kingsley
1c675522fd [data] Fix glm4v mmplugin when not expand (#9029) 2025-08-27 11:45:24 +08:00
Kingsley
1639e4b587 [data] fix gemma3n mmplugin (#8627) 2025-07-14 13:32:57 +08:00
Kingsley
542fa97a72 [data] support glm4.1v video training (#8571) 2025-07-08 16:29:44 +08:00
Yaowei Zheng
4b0ec83928 [deps] bump transformers to 4.49.0 (#8564) 2025-07-07 20:31:50 +08:00
Kingsley
e9f70daabe [model] add gemma3n (#8509) 2025-07-01 22:37:24 +08:00
Kingsley
d17a672251 [model] add GLM-4.1V (#8462) 2025-06-30 01:09:41 +08:00
Yaowei Zheng
48897e5b16 [data] fix audio reader (#8448) 2025-06-24 20:53:20 +08:00
Kingsley
31bca4d172 [model] support Mistral3.1 small 2503 (#8335) 2025-06-09 10:37:42 +08:00
Kingsley
c224d17cb2 [data] support nested images input for videos (#8264) 2025-06-03 20:26:29 +08:00
Kingsley
f08b748199 [data] fix internvl plugin when using PIL images (#8129) 2025-05-22 01:32:59 +08:00
hoshi-hiyouga
9ae17cd173 [deps] update to transformers 4.52 (#8125) 2025-05-21 05:16:18 +08:00
hoshi-hiyouga
beae231af6 [doc] add no build isolation (#8103) 2025-05-19 19:25:13 +08:00
Kingsley
52b23f9e56 [data] add forward compatibility for video_utils in Transformers 4.52.0 (#8077) 2025-05-16 17:41:04 +08:00
hoshi-hiyouga
68fc068cab [data] fix kimi vl template (#8015) 2025-05-11 20:45:19 +08:00
hoshi-hiyouga
c566e39b7d [data] fix base plugin (#7924) 2025-04-30 16:28:05 +08:00
hoshi-hiyouga
11295cdea0 [data] improve mm plugin (#7910) 2025-04-30 06:34:28 +08:00
Kingsley
db9559456c [data] fix qwen2.5 omni template (#7883) 2025-04-29 00:58:23 +08:00
hoshi-hiyouga
3ae5da2a04 [model] fix dsv3 leaf node (#7879) 2025-04-28 18:11:09 +08:00
hoshi-hiyouga
d173cb50f5 [data] fix qwen2 omni plugin (#7875) 2025-04-28 14:22:41 +08:00
hoshi-hiyouga
bb5b83352b [data] fix minicpmo vllm infer (#7870) 2025-04-28 01:59:53 +08:00
Kingsley
fa0eb91f1f [data] fix internvl plugin (#7817) 2025-04-23 00:58:22 +08:00
Kingsley
7500e761d3 [misc] update internvl constants (#7801) 2025-04-22 15:53:08 +08:00
hoshi-hiyouga
0e4ce039ee [data] improve mmplugin (#7795) 2025-04-22 01:25:33 +08:00
hoshi-hiyouga
39169986ef [trainer] fix pt loss (#7748)
* fix pt loss

* robust

* fix

* test
2025-04-17 03:15:35 +08:00
hoshi-hiyouga
86ebb219d6 [breaking] bump transformers to 4.45.0 & improve ci (#7746)
* update ci

* fix

* fix

* fix

* fix

* fix
2025-04-17 02:36:48 +08:00
Kingsley
2e518f255f [model] support intern-VL 2.5-3 series (#7258)
* add internvl and rebase

* fix for internvl2&3

* remove lines

* fix video_inputs & lint

* nit

* add constants

* remove lines

* fix

* fix error

* pass ci

* pass ci

* skip internvl & nit
2025-04-17 00:31:30 +08:00
Kingsley
2101399c94 [model] Support Kimi_VL thinking/instruct (#7719)
* add kimi_vl

* patch config

* check version

* Update mm_plugin.py

* Update mm_plugin.py

---------

Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
2025-04-15 00:21:58 +08:00
Kingsley
349c56c51c [data] Fix bugs of use_audio_in_video in Qwen2.5 Omni (#7638)
* cache _mm_inputs

* nit

* support for use_audio_in_video

* remove cache

* fix data

* Update mllm_video_audio_demo.json
2025-04-08 18:40:10 +08:00
hoshi-hiyouga
c3c0efbaa0 [misc] fix packing and eval plot (#7623) 2025-04-07 18:20:57 +08:00
hoshi-hiyouga
831e7f1cfd [model] add llama4 (#7611) 2025-04-06 13:42:31 +08:00
Kingsley
d4cfa9507e [data] fix qwen2.5 omni plugin (#7578)
* specific entry

* Update mm_plugin.py

* fix fps cal

---------

Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
2025-04-02 23:58:39 +08:00
Kingsley
d32c6c014d [data] fix qwen2.5 omni plugin (#7573)
* align key with qwen2vl

* nit && change scripts
2025-04-02 21:28:52 +08:00
hoshi-hiyouga
5e22597ff1 [infer] vllm video/audio inference (#7566) 2025-04-02 02:27:04 +08:00
hoshi-hiyouga
2bfcad2394 [model] fix kv cache (#7564) 2025-04-01 23:07:46 +08:00
Kingsley
7eed496336 [model] add Qwen2.5-Omni model (#7537)
* preserve image_sizes

* preserve image_sizes

* init plugin

* support audio-text2text lora

* nit

* support image/video-text2text, audio-text2text

* remove args

* remove lines

* add docs && nit

* remove some comments

* fix && add merge part script

* add license
2025-03-31 20:39:35 +08:00
Kingsley
8da1d2fa71 [data] fix pixtral plugin (#7505)
* preserve `image_sizes`

* add comments
2025-03-27 17:06:40 +08:00
hoshi-hiyouga
7203365b80 [trainer] fix vlm loss for transformers 4.49 (#7448) 2025-03-24 10:24:05 +08:00
hoshi-hiyouga
93e6184cbe [data] gemma3 plugin pan and scan (#7294)
* gemma3 pan and scan

* add test case

* fix test
2025-03-13 23:29:23 +08:00
hoshi-hiyouga
650a9a9057 [misc] update format (#7277) 2025-03-13 02:53:08 +08:00
hoshi-hiyouga
4b9d8da5a4 [model] support gemma3 (#7273) 2025-03-13 01:35:23 +08:00
hoshi-hiyouga
264538cb26 [misc] upgrade format to py39 (#7256) 2025-03-12 00:08:41 +08:00
hoshi-hiyouga
bb8aba5abf [data] fix mm template (#7181)
Former-commit-id: 648616d473c81d393592806307e3e25b159cb278
2025-03-06 15:18:32 +08:00
hoshi-hiyouga
7b985f55db [trainer] update config (#7174)
Former-commit-id: 9f535d0e3c4ee3cd0f1b65218c2eee5d03f43c6f
2025-03-05 23:32:54 +08:00