Commit Graph

2002 Commits

Author SHA1 Message Date
hoshi-hiyouga
036fb0d561 [misc] fix grad ckpt func (#6916)
Former-commit-id: e34c3c06da
2025-02-13 00:17:18 +08:00
marko1616
bae934dea3 [trainer] fix llama3.2 vision kto train (#6904)
Former-commit-id: b7fd1e9c00
2025-02-12 19:09:14 +08:00
hoshi-hiyouga
2e2f6bea07 [data] feat: auto template (#6905)
* support auto template

* add unittest

Former-commit-id: 2f8b6847f5
2025-02-12 00:22:53 +08:00
hoshi-hiyouga
197aa3baf4 [data] fix ollama template (#6902)
* fix ollama template

* add meta info

* use half precision

Former-commit-id: e1a7c1242c
2025-02-11 22:43:09 +08:00
hoshi-hiyouga
c6be9e242c [misc] support export ollama modelfile (#6899)
* support export ollama modelfile

* update config

* add system and num ctx

Former-commit-id: 9184a6e0ed
2025-02-11 19:52:25 +08:00
hoshi-hiyouga
2e954d8fd2 [data] refactor template (#6896)
Former-commit-id: d1b8aa3835
2025-02-11 17:59:25 +08:00
hoshi-hiyouga
593acca556 [data] refactor mm plugin (#6895)
* refactor plugin

* lint

Former-commit-id: aca63bfcca
2025-02-11 16:34:49 +08:00
HJ
188f22d8a7 [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: 9153a7bd83
2025-02-11 16:14:50 +08:00
Zhangchi Feng
5433b318bb [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: 764627645a
2025-02-11 13:30:44 +08:00
HJ
fe4f4e9758 [data] fix: sharegpt converter (#6879)
* fix-sharegpt-format

* fix

---------

Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: 0fb44cb3a5
2025-02-10 21:59:12 +08:00
hoshi-hiyouga
1bb3d17d9e [data] fix mllama collator (#6874)
Former-commit-id: b68199db27
2025-02-09 22:42:25 +08:00
hoshi-hiyouga
b93333685b [test] align test cases (#6865)
* align test cases

* fix function formatter

Former-commit-id: f6f3f8d0fc
2025-02-09 01:03:49 +08:00
hoshi-hiyouga
fcd0f0480d [dataset] add openthought (#6866)
Former-commit-id: 1356f9d840
2025-02-09 00:53:01 +08:00
hoshi-hiyouga
ff6658ad27 [deps] upgrade vllm (#6857)
Former-commit-id: 5f38bcaba9
2025-02-08 15:02:28 +08:00
hoshi-hiyouga
28037c7834 fix qwen2vl plugin (#6855)
Former-commit-id: 40048ab77a
2025-02-08 10:59:10 +08:00
hoshi-hiyouga
f70208e1c0 [misc] allow extra args (#6831)
Former-commit-id: 74ade3a176
2025-02-06 12:38:08 +08:00
Zhangchi Feng
01915eaf40 [model] support audio (#6701)
* support qwen2_audio

* improve code

* lint

* fix

* fix

* fix

---------

Co-authored-by: hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: 24c7842948
2025-02-05 04:59:09 +08:00
Yueqi Song
e665e1fed5 [data] allow thought in function call (#6797)
* Update template.py

* Update template.py

* use formatter

* fix regex

---------

Co-authored-by: hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: a5e943f7bc
2025-02-05 02:26:23 +08:00
hoshi-hiyouga
1fee69f874 [misc] update license year & fix llama pro (#6814)
* fix llamapro script

* change year

Former-commit-id: e2dc5b952a
2025-02-05 01:53:33 +08:00
Yueqi Song
8504bde893 [data] fix qwen tool template (#6796)
* Update tool_utils.py

* fix unittest

---------

Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: dd6b7d203e
2025-02-05 00:02:00 +08:00
Zhangchi Feng
85f22d01bf [data] fix minicpmv plugin (#6801)
* 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

Former-commit-id: ab9bd068ef
2025-02-04 21:20:15 +08:00
hoshi-hiyouga
445d643ef3 [model] add mistral small models (#6786)
Former-commit-id: 94803d8133
2025-02-01 04:31:38 +08:00
hoshi-hiyouga
e8c1979b79 [model] add qwen2.5 vl models (#6779)
Former-commit-id: 999c7c8fe0
2025-01-31 03:00:29 +08:00
hoshi-hiyouga
f6779b0e0c [breaking] support transformers 4.48 (#6628)
Former-commit-id: 15357cdad9
2025-01-31 01:36:33 +08:00
hoshi-hiyouga
245de012ca [webui] improve webui & reasoning mode (#6778)
Former-commit-id: 45e68b9f09
2025-01-31 00:09:21 +08:00
qvlehao
f5350b103b [model] add deepseek-R1 & show think process (#6767)
Former-commit-id: 28417f862a
2025-01-29 12:16:26 +08:00
yinpu
aa7c07caf0 fix: avoid redundant normalization in DPO's SFT loss calculation (#6722)
Former-commit-id: 0f45982bac
2025-01-21 13:38:02 +08:00
engchina
324f07613a [webui] support ja (#6698)
* add support for japanese language

* add support for japanese language

---------

Co-authored-by: engchina <atjapan2015@gmail.com>
Former-commit-id: de9bc3fefa
2025-01-20 19:46:38 +08:00
hoshi-hiyouga
1efe525df7 [model] support yarn (#6693)
Former-commit-id: 1f47b6186c
2025-01-18 13:56:09 +08:00
hoshi-hiyouga
f87c788154 [misc] update mm plugin (#6691)
Former-commit-id: c0caa7afc6
2025-01-17 23:04:26 +08:00
hoshi-hiyouga
bbf334f823 disable valset by default (#6690)
Former-commit-id: 77bbf65905
2025-01-17 21:09:30 +08:00
hoshi-hiyouga
770433fa33 [webui] upgrade to gradio 5 (#6688)
Former-commit-id: 4d0f662dbe
2025-01-17 20:15:42 +08:00
hoshi-hiyouga
788accb601 fix qwen2 moe (#6684)
Former-commit-id: 7bf09abf1c
2025-01-17 13:46:09 +08:00
Zhangchi Feng
555f17c1ee [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

Former-commit-id: 027942789b
2025-01-15 17:30:37 +08:00
steveepreston
8895cf1152 Update val_size english description (#6653)
* Update `val_size` Description in locales.py

* Update `val_size` Description in data_args.py

* Remove extra space in data_args.py

Former-commit-id: 76675b654e
2025-01-15 16:00:20 +08:00
hoshi-hiyouga
9ef85f8fc4 [optim] clean apollo (#6645)
* clean apollo code

* update readme

Former-commit-id: 7a04021d04
2025-01-15 01:42:50 +08:00
zhuHQ
763f9b9df0 [optim] add support to APOLLO (#6617)
Former-commit-id: d9189f9f0b
2025-01-15 00:24:56 +08:00
hoshi-hiyouga
91433d639c lint (#6641)
Former-commit-id: 1278c3e92e
2025-01-14 18:40:07 +08:00
Haian Huang(深度眸)
864ee06243 Support InternLM3 Dense 8B Model (#6640)
* support internlm3

* update

* update

* update

* add hint

Former-commit-id: deacc00b12
2025-01-14 18:07:27 +08:00
Xiaosu Zhu
a52496cc09 Fix tokenizer max length (#6632)
Former-commit-id: 58d029f321
2025-01-14 17:35:54 +08:00
Zhangchi Feng
ad119afc58 Support Inference of MiniCPM-V-2.6 and MiniCPM-o-2.6 (#6631)
* fix template name

* tiny fix

* support minicpm-o-2.6

* support inference of minicpmv

Former-commit-id: 158a127d34
2025-01-14 17:34:58 +08:00
hoshi-hiyouga
8f73c75c16 [model] fix mllama any image (#6637)
* fix mllama any image

* reorder classes

Former-commit-id: 98189c8e4d
2025-01-14 16:47:58 +08:00
hoshi-hiyouga
5e699458e5 pin vllm version to 0.6.5 (#6629)
Former-commit-id: 1c7663d304
2025-01-14 02:44:02 +08:00
Zhangchi Feng
201a495154 Support new features of MiniCPM-V (#6626)
* fix template name

* tiny fix

* support minicpm-o-2.6

Former-commit-id: c3fda5046d
2025-01-14 00:26:19 +08:00
hoshi-hiyouga
d8cba9464f [inference] fix stop token for object detection (#6624)
* fix stop token

* update minicpm data pipeline

* fix npu qlora examples

Former-commit-id: e3e2c8c689
2025-01-13 21:34:20 +08:00
codingma
089c7d5e51 add nf4 qlora support on Ascend NPU (#6601)
* add nf4 qlora support on Ascend NPU

* add transformers version check

* add python>=3.10 requirement description for npu

* tiny fix

---------

Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Former-commit-id: 03de5ac912
2025-01-13 19:43:36 +08:00
Zhangchi Feng
15bba15725 Fix template name of MiniCPM-V (#6620)
* fix template name

* tiny fix

Former-commit-id: 3077f20339
2025-01-13 16:46:48 +08:00
fzc8578
313ce9a576 remove tests
Former-commit-id: a019cece80
2025-01-13 15:08:35 +08:00
fzc8578
4741eec2d1 fix style
Former-commit-id: 0cc7260a93
2025-01-13 14:19:38 +08:00
fzc8578
d2afe0c63c fix system prompt and tests
Former-commit-id: cfaa8e4890
2025-01-13 14:18:06 +08:00