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
hoshi-hiyouga
51821b91ae
[data] use bicubic resampler ( #7143 )
...
Former-commit-id: c708f19ab0ab57526134952afddaa90aae8decbf
2025-03-04 00:17:06 +08:00
rabbit
7c0684a2cf
[data] bailing template ( #7117 )
...
* add bailing template
* add bailing template
* add bailing template
---------
Co-authored-by: chengshiwen.csw@antgroup.com <chengshiwen.csw@antgroup.com>
Former-commit-id: 4a36f5e0abb5a63f4b3b81560bb1ad0e6832d379
2025-03-03 15:33:22 +08:00
hoshi-hiyouga
76f860a228
[data] fix mllama ( #7053 )
...
* fix mllama
* fix test
Former-commit-id: f5af20a63f3d59a6a68d323a7c6f68e551edb3a3
2025-02-24 22:05:38 +08:00
hoshi-hiyouga
a354df6d90
[model] add models ( #7054 )
...
* add qwen25vl awq models
* add moonlight
Former-commit-id: ae3be2970fea8a35907202a313ab767381c44916
2025-02-24 22:05:13 +08:00
Zhangchi Feng
354a0a28b3
[data] fix MiniCPMV plugin ( #6998 )
...
* fix template
* fix bug in messages processing
Former-commit-id: f98b828f53968fb9c72bff9e45510ad5586c4fab
2025-02-19 19:36:04 +08:00
hoshi-hiyouga
865b2b8b87
[version] support transformers 449 ( #6982 )
...
* support transformers 449
* fix mm plugin
Former-commit-id: e9118a9df0839d24f6ddff5a0b55ef101a1d3d22
2025-02-18 17:05:40 +08:00
hoshi-hiyouga
ccc656376f
[misc] fix script ( #6977 )
...
Former-commit-id: 775efa1d8cbdb1b7d122be2a986d47f85214e0a1
2025-02-18 17:00:46 +08:00
hoshi-hiyouga
5deefc6094
[data] update vlm args ( #6976 )
...
Former-commit-id: c28e710636a0286d4b8a1d494529b25168a8f3ab
2025-02-18 02:12:51 +08:00
hoshi-hiyouga
b7ccfd28d1
[data] add min resolution option ( #6975 )
...
Former-commit-id: 76bd9a98a2fb00f1a1d881e6e1364c02fd36d327
2025-02-18 01:40:46 +08:00
hoshi-hiyouga
4e661b63e3
[data] fix predict dataset ( #6972 )
...
Former-commit-id: f9a82e527877b1ed47cabb3d34f4d155705f4048
2025-02-17 20:29:40 +08:00
Zhangchi Feng
69fcc8e0c0
[data] fix minicpmo template ( #6946 )
...
Former-commit-id: 09e4438b58d5c1a5fdde37ff781c3d79461c4743
2025-02-15 00:37:41 +08:00
hoshi-hiyouga
1cda37892e
[misc] fix lora regex ( #6944 )
...
* fix lora regex
* fix
Former-commit-id: 1d0ecbaee1b72f1e03154ddd4fcc8b7876e01f89
2025-02-14 21:38:43 +08:00
SrWYG
d9ea4baf00
[data] evaluate on each dataset ( #5522 )
...
* [Update] loader.py , evaluate will run separate evaluations on each dataset.
`If you pass a dictionary with names of datasets as keys and datasets as values, evaluate will run separate evaluations on each dataset. This can be useful to monitor how training affects other datasets or simply to get a more fine-grained evaluation`
seq2seqtrainner support eval_dataset as Dict.
* fix format
* fix
* fix
---------
Co-authored-by: hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: cf00f78650a442c85678ce805e030d2b96cbecd7
2025-02-13 02:19:03 +08:00
Noah
f1c2ae9d47
[data] improve error handling ( #6128 )
...
* sync from upstream
* update
* update
* fix
---------
Co-authored-by: hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: 1569e6096fec07da5583f1a3435b0d23ae09b5ba
2025-02-13 01:39:41 +08:00
hoshi-hiyouga
efef4eaefc
[breaking change] refactor data pipeline ( #6901 )
...
* refactor data
* rename file
Former-commit-id: 7a1a4ce6451cb782573d0bd9dd27a5e443e3a18b
2025-02-13 00:39:20 +08:00
marko1616
a23e16ae89
[trainer] fix llama3.2 vision kto train ( #6904 )
...
Former-commit-id: 1563e89adc8988fc6e4250634a3f1e385979b0e5
2025-02-12 19:09:14 +08:00
hoshi-hiyouga
0a0d7671e0
[data] feat: auto template ( #6905 )
...
* support auto template
* add unittest
Former-commit-id: 0c6c9150db6414a5a05527ea486dce6633dff4b3
2025-02-12 00:22:53 +08:00
hoshi-hiyouga
c5649d7149
[data] fix ollama template ( #6902 )
...
* fix ollama template
* add meta info
* use half precision
Former-commit-id: 1304bbea69d8c8ca57140017515dee7ae2ee6536
2025-02-11 22:43:09 +08:00
hoshi-hiyouga
ca5cd8276c
[misc] support export ollama modelfile ( #6899 )
...
* support export ollama modelfile
* update config
* add system and num ctx
Former-commit-id: 8c2af7466f4015f300b51841db11bcd2505ebf20
2025-02-11 19:52:25 +08:00
hoshi-hiyouga
5954d4cfbc
[data] refactor template ( #6896 )
...
Former-commit-id: f78d5a3eca947ed965ca2f6c87d60441b1a59867
2025-02-11 17:59:25 +08:00
hoshi-hiyouga
64069e75d7
[data] refactor mm plugin ( #6895 )
...
* refactor plugin
* lint
Former-commit-id: 1c8dcc3adca4a2e78f514f8bb70573dd1ca08746
2025-02-11 16:34:49 +08:00
HJ
02264873fd
[data] fix qwen_2_5_vl video processing ( #6868 )
...
* fix qwen_2_5_vl video processing
* Update mm_plugin.py
* Update mm_plugin.py
---------
Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: 35f326dabdc8e84036296d2e3de1c84c67b8def8
2025-02-11 16:14:50 +08:00
Zhangchi Feng
5cf98e2084
[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
Former-commit-id: cdd19ccd8cec460606b4545e886e932c1c5c5fe1
2025-02-11 13:30:44 +08:00
HJ
96b6865ba5
[data] fix: sharegpt converter ( #6879 )
...
* fix-sharegpt-format
* fix
---------
Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: ae8f8151ff750839998b50446f127061f240d41a
2025-02-10 21:59:12 +08:00
hoshi-hiyouga
4d30538c03
[data] fix mllama collator ( #6874 )
...
Former-commit-id: c694fa3d66651c6ce547fa72c8260c46a406126b
2025-02-09 22:42:25 +08:00
