hoshi-hiyouga
634efb3ac9
[model] add qwen2 omni 3b ( #7945 )
2025-05-03 16:36:51 +08:00
hoshi-hiyouga
0f33e040bf
[data] fix base plugin ( #7924 )
2025-04-30 16:28:05 +08:00
hoshi-hiyouga
0af4d834ef
[data] optimize qwen3 loss computation ( #7923 )
2025-04-30 16:18:00 +08:00
hoshi-hiyouga
23bc89c80c
[data] add eval_on_each_dataset arg ( #7912 )
2025-04-30 06:56:43 +08:00
hoshi-hiyouga
142a071309
[data] replace eos token for base models ( #7911 )
2025-04-30 06:52:28 +08:00
hoshi-hiyouga
5bb88f7dc9
[data] improve mm plugin ( #7910 )
2025-04-30 06:34:28 +08:00
hoshi-hiyouga
660ceaaa3f
[model] add qwen3 ( #7885 )
2025-04-29 09:34:05 +08:00
Kingsley
a3869a6514
[data] fix qwen2.5 omni template ( #7883 )
2025-04-29 00:58:23 +08:00
hoshi-hiyouga
f7275e1ef5
[model] fix dsv3 leaf node ( #7879 )
2025-04-28 18:11:09 +08:00
hoshi-hiyouga
8908a85465
[data] fix qwen2 omni plugin ( #7875 )
2025-04-28 14:22:41 +08:00
hoshi-hiyouga
f6bb4c3f8e
[data] fix minicpmo vllm infer ( #7870 )
2025-04-28 01:59:53 +08:00
Kingsley
000dbfe144
[data] fix internvl plugin ( #7817 )
2025-04-23 00:58:22 +08:00
Kingsley
52eeb0fc4f
[misc] update internvl constants ( #7801 )
2025-04-22 15:53:08 +08:00
hoshi-hiyouga
acf641abc2
[data] improve mmplugin ( #7795 )
2025-04-22 01:25:33 +08:00
Changrui Chen
314bcb3f36
[data] Fix wrong position ids with packed attention masks ( #7754 )
...
Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
2025-04-21 23:19:36 +08:00
hoshi-hiyouga
8208cbf1dc
[trainer] fix pt loss ( #7748 )
...
* fix pt loss
* robust
* fix
* test
2025-04-17 03:15:35 +08:00
hoshi-hiyouga
a0818eae58
[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
7a00670f70
[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
d1b695cd9f
[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
Eric Tang
45c5a913f8
[data] support for specifying a dataset in cloud storage ( #7567 )
...
* add support for loading datasets from s3/gcs
* add comments to readme
* run linter and address comments
* add option to pass in kwargs to ray init (i.e. runtime env)
* address comment
* revert mixed up changes
2025-04-10 11:31:35 +08:00
hoshi-hiyouga
458b6b0aef
[assets] update readme ( #7644 )
2025-04-09 01:06:06 +08:00
Kingsley
0935eff188
[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
fb46193364
[misc] fix packing and eval plot ( #7623 )
2025-04-07 18:20:57 +08:00
hoshi-hiyouga
40fb24916f
[model] add llama4 ( #7611 )
2025-04-06 13:42:31 +08:00
Kingsley
6eb28bcacd
[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
ac9ba80128
[data] fix qwen2.5 omni plugin ( #7573 )
...
* align key with qwen2vl
* nit && change scripts
2025-04-02 21:28:52 +08:00
hoshi-hiyouga
be0289292d
[infer] vllm video/audio inference ( #7566 )
2025-04-02 02:27:04 +08:00
hoshi-hiyouga
37d783149d
[model] fix kv cache ( #7564 )
2025-04-01 23:07:46 +08:00
Ritesh Goru
917264f79f
[data] specify position_ids in PackedSupervisedDatasetProcessor for neat_packing ( #7318 )
...
* use position_ids for neat_packing with fa2
* revert fa2 changes
2025-04-01 16:03:13 +08:00
Billy Cao
51e741ec85
[data] shard the dataset to allow multiprocessing when streaming is enabled ( #7530 )
...
* Shard the dataset when streaming to allow multiprocessing
* Allow user to not set dataset_shards to ensure backward compatibility
2025-04-01 15:36:23 +08:00
Hao
538e6c70c3
[trainer] new kto mismatch pair creation strategy ( #7509 )
2025-04-01 15:21:53 +08:00
hoshi-hiyouga
56fa64035a
[data] fix qwen2.5 omni collator ( #7553 )
2025-04-01 00:15:12 +08:00
Kingsley
1189aeb6c2
[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
bde7d60f4e
[data] fix pixtral plugin ( #7505 )
...
* preserve `image_sizes`
* add comments
2025-03-27 17:06:40 +08:00
hoshi-hiyouga
180019b376
[trainer] fix vlm loss for transformers 4.49 ( #7448 )
2025-03-24 10:24:05 +08:00
hoshi-hiyouga
1a7c872c14
[deps] upgrade transformers to 4.50.0 ( #7437 )
...
* upgrade transformers
* fix hf cache
* fix dpo trainer
2025-03-23 17:44:27 +08:00
hoshi-hiyouga
99edc530e3
[assets] update wechat ( #7361 )
2025-03-18 21:31:09 +08:00
hoshi-hiyouga
2a13067a42
[data] fix template ( #7349 )
2025-03-17 23:45:20 +08:00
Hertz
db936dc329
[model] support hunyuan 7b ( #7317 )
...
* [Model]supported tencent-hunyuan model
* [Model]supported tencent-hunyuan model(fix)
* [Model]supported tencent-hunyuan model(fix)
2025-03-15 20:55:24 +08:00
hoshi-hiyouga
e7ae755ab6
[data] gemma3 plugin pan and scan ( #7294 )
...
* gemma3 pan and scan
* add test case
* fix test
2025-03-13 23:29:23 +08:00
Ritesh Goru
f5b53249a4
[data] efficient 4d_attention_mask creation in neat_packing ( #7272 )
2025-03-13 03:31:12 +08:00
hoshi-hiyouga
1b1964714e
[misc] update format ( #7277 )
2025-03-13 02:53:08 +08:00
hoshi-hiyouga
a54c859674
[model] support gemma3 ( #7273 )
2025-03-13 01:35:23 +08:00
hoshi-hiyouga
efa86e730c
[misc] upgrade format to py39 ( #7256 )
2025-03-12 00:08:41 +08:00
hiyouga
ec251b4614
remove exit in preprocess
...
Former-commit-id: f369b6ef41ffd9586ba568b88c5ff32a1af4bace
2025-03-11 15:08:25 +08:00
hoshi-hiyouga
8c7917d1a2
[data] fix loader ( #7207 )
...
* fix dataloader
* add test case
* fix type
* fix ci
* fix ci
* fix ci
* disable overwrite cache in ci
Former-commit-id: e84af0e140b1aafd1a6d6fe185a8e41c8fc5f831
2025-03-07 17:20:46 +08:00
ZhangChuanhui
ee9bd3f2d7
[data] fix function formatter ( #7201 )
...
Co-authored-by: zhangchuanhui <zhangchal@digitalchina.com>
Former-commit-id: 3efb32b986170d2839e526640f85ba230715879a
2025-03-07 15:17:23 +08:00
hoshi-hiyouga
26fddbd7c4
[data] fix mm template ( #7181 )
...
Former-commit-id: 648616d473c81d393592806307e3e25b159cb278
2025-03-06 15:18:32 +08:00
hoshi-hiyouga
54bcc37f55
[trainer] update config ( #7174 )
...
Former-commit-id: 9f535d0e3c4ee3cd0f1b65218c2eee5d03f43c6f
2025-03-05 23:32:54 +08:00
sirui.li
58943fa554
[data] fix qwen2audio plugin ( #7166 )
...
* Update pairwise.py
[data]Repair multimodal model dpo training
* Update pairwise.py
[data]repair multimodal model dpo training using deepcopy
* Update pairwise.py
* Update mm_plugin.py
Former-commit-id: 86763dfdb8e9e5668c1ddd7e924e4be76bf78368
2025-03-05 18:03:36 +08:00
