Ritesh Goru
d7d79f7e06
[data] efficient 4d_attention_mask creation in neat_packing ( #7272 )
2025-03-13 03:31:12 +08:00
hoshi-hiyouga
9ccfb97a2c
[misc] update format ( #7277 )
2025-03-13 02:53:08 +08:00
hoshi-hiyouga
7c1640ed5f
[misc] upgrade format to py39 ( #7256 )
2025-03-12 00:08:41 +08:00
hoshi-hiyouga
3fbd4848e8
[version] support transformers 449 ( #6982 )
...
* support transformers 449
* fix mm plugin
Former-commit-id: b00b290c07beb560a5af857ce64f4ce424831a2c
2025-02-18 17:05:40 +08:00
marko1616
bae934dea3
[trainer] fix llama3.2 vision kto train ( #6904 )
...
Former-commit-id: b7fd1e9c00c77a4c2a0f2f347767d22bd47213f1
2025-02-12 19:09:14 +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: 764627645abcd353f9130d5dd8c584810b0e0b1b
2025-02-11 13:30:44 +08:00
hoshi-hiyouga
1bb3d17d9e
[data] fix mllama collator ( #6874 )
...
Former-commit-id: b68199db274a53d5916179e1aaf9722fd94fa2dc
2025-02-09 22:42:25 +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: 24c78429489809873a1269a735ea5421340b32a2
2025-02-05 04:59:09 +08:00
hoshi-hiyouga
e8c1979b79
[model] add qwen2.5 vl models ( #6779 )
...
Former-commit-id: 999c7c8fe0caf6b837a1bdc2c6a24fafec327cd8
2025-01-31 03:00:29 +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: 027942789bf3a28b2506a5730c05c8392ef5c885
2025-01-15 17:30:37 +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: c3fda5046d835ba4542d525b8d89cd12838e9f4c
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: e3e2c8c689c54ebb2af264de808502e5a8ba0f2b
2025-01-13 21:34:20 +08:00
fzc8578
4741eec2d1
fix style
...
Former-commit-id: 0cc7260a93bf7c65451e376245aa143f9237d7d8
2025-01-13 14:19:38 +08:00
fzc8578
d2afe0c63c
fix system prompt and tests
...
Former-commit-id: cfaa8e4890ad99ec1fb90d9550503d734b5c30b7
2025-01-13 14:18:06 +08:00
fzc8578
e7f928adc4
fix format
...
Former-commit-id: 7b44f3127ef7e91a6bedca0311feb14974914ddf
2025-01-11 01:27:40 +08:00
fzc8578
62c12a133e
add some
...
Former-commit-id: a650e114e907278ece188922467c2514de544eeb
2025-01-11 01:10:24 +08:00
fzc8578
08e8499a98
adapt to new mllm_param
...
Former-commit-id: 291384dea8a5c10f0358a30d124eaf85557548eb
2025-01-11 00:16:34 +08:00
fzc8578
0fb50f9c88
add some
...
Former-commit-id: 771cc802941cf1953b32e5102c817c6a3090b5ce
2025-01-10 23:29:06 +08:00
fzc8578
bcbe37ff52
add some
...
Former-commit-id: ae1f528df31194fe37a123ba1e5a4cd263a61602
2025-01-10 21:25:32 +08:00
fzc8578
7138b43873
fix some
...
Former-commit-id: 2ee8ba2f390551af1b865cfa813f5c8b7bbb41c5
2025-01-10 20:27:06 +08:00
fzc8578
165fe8e219
add some
...
Former-commit-id: 096a6cb67a7dfd14a6e339d96baab78c12d36a87
2025-01-10 20:01:22 +08:00
fzc8578
b5ef5059ee
add some
...
Former-commit-id: 79c2d7090cbf364063ea3608814ab18aa27fdc87
2025-01-04 11:11:15 +08:00
hiyouga
813f5919a3
fix #6482
...
Former-commit-id: 6f5bb3b8e5b6eb7fdfd7b0ca8eba789ab741a7b6
2024-12-30 06:03:07 +00:00
hiyouga
3bcb4633ca
fix #6448
...
Former-commit-id: 27198679829fb766c7eef468ae4311fdced695a2
2024-12-27 16:54:39 +00:00
hiyouga
50ca43c3fb
fix #6348
...
Former-commit-id: 142191e4664cb1b920aff2f51d1bac6180f2c24b
2024-12-17 10:06:46 +00:00
hiyouga
6f1e450739
fix mrope
...
Former-commit-id: 2811814fc42fb214b3e8be1055f9f57ffd0ffb12
2024-12-12 15:08:17 +00:00
hiyouga
819f487c8f
fix scripts
...
Former-commit-id: eb3e147d198a3ecb02c65f7733cec7cd9d3814a3
2024-12-05 03:47:32 +00:00
hiyouga
0ef1dc4dd5
fix vlm zero3 training
...
Former-commit-id: dbb9e5b70efab37ed057b2d5822b9d0d23e99fb1
2024-12-04 09:40:39 +00:00
hiyouga
006022cadd
fix mllama cross_mask
...
Former-commit-id: 598c22e43f3f10a335933339cc612744c4835eb0
2024-11-26 15:56:58 +00:00
hiyouga
e99031daa4
fix inputs
...
Former-commit-id: 446441fdb020b5a102480251cb8536dd8b3f8f99
2024-11-23 18:26:02 +00:00
hoshi-hiyouga
fb8f35558a
Update collator.py
...
Former-commit-id: f745c4b28f532c7084d4b8522c972e735729ecee
2024-10-29 22:03:42 +08:00
Kingsley
3053a806e9
Merge branch 'hiyouga:main' into pixtral-patch
...
Former-commit-id: 67f59579d79e97689a4b3cba7101a423c30dab2b
2024-10-29 21:01:25 +08:00
hiyouga
0d8aa6e6ef
use pre-commit
...
Former-commit-id: 21db8ed2f4a0eba203754a92ce0741538e8ee709
2024-10-29 09:07:46 +00:00
KUANGDD
62cbcb646a
modify style & little change
...
Former-commit-id: 9d6143e36a12e0f295139d057aeb1843535435cf
2024-10-23 15:24:07 +08:00
hiyouga
995491594d
tiny fix
...
Former-commit-id: 76f2e5950483c669a15a961f0554442b6eb5c4a6
2024-09-05 23:41:16 +08:00
hiyouga
9df7a26e6b
video datasets
...
Former-commit-id: 8cafc7b055a854f483ad1c67f3d487ffd34b5f89
2024-09-05 02:04:17 +08:00
hiyouga
22deca0e9e
lazy image load
...
Former-commit-id: 47ea97fb1ba77de2e8a561904aa8fdc27c3f5025
2024-09-04 02:27:08 +08:00
hiyouga
bfdcc6bacf
add rlhf-v dataset
...
Former-commit-id: 8e49940746c1a6ff910f07dbefbec14af9d0f3c6
2024-09-01 22:57:41 +08:00
hiyouga
413a206652
fix bug
...
Former-commit-id: 64cb947c60398dfdfc2877f898147b0240089ea3
2024-09-01 21:07:49 +08:00
hiyouga
cb776752f6
fix mixed mm inputs and rlhf-v
...
Former-commit-id: 9967ccb3aef3ca557ad6eafb78c6c99866857008
2024-09-01 20:52:47 +08:00
hiyouga
92c398166d
tiny fix
...
Former-commit-id: bee1bd43b946501690d70e4980205f9d82404296
2024-08-30 03:21:50 +08:00
hiyouga
a83756b5e9
refactor mm training
...
Former-commit-id: 3382317e32f88ed377d3e7759bdeaf0f2559d22a
2024-08-30 02:14:31 +08:00
simonJJJ
8a09b1e732
initial-commit
...
Former-commit-id: aeb85f200bd824748008dae6047c2607dfcdf174
2024-08-28 16:51:35 +08:00
hiyouga
0b26011181
fix gemma2 attention
...
Former-commit-id: 2f6af73da28c4f8321b625fd09ddec8bd4977b08
2024-07-13 23:33:45 +08:00
hzhaoy
6d892dbc23
tiny fix
...
Former-commit-id: 738df477485de3633049651a9f1d498adf95a3d5
2024-07-04 10:20:28 +08:00
hiyouga
7b3c1f29ff
fix packing for eager/sdpa attn
...
Former-commit-id: 6fd6aa4530f81a2ed306eeb2a5167607288b62c6
2024-07-04 01:52:43 +08:00
hiyouga
bfdaadcc40
update packing
...
Former-commit-id: cce7083024bed4c7429ddc8288d1c9190fde29f5
2024-07-04 01:10:55 +08:00
hiyouga
ff6fc666c1
update hparams
...
Former-commit-id: 575a02a23d9b41d00ca6291d8a40b5bdb3cbeeec
2024-07-03 23:18:58 +08:00
hiyouga
2946153cea
add license
...
Former-commit-id: d87108daa68bd40174b262be1ca65fe6e1b7ab56
2024-06-15 17:54:33 +08:00
hiyouga
3e729798df
refactor data preprocessing, fix mllm rlhf
...
Former-commit-id: 3a023bca2a502810a436cfba7708df164754ea62
2024-05-24 04:08:25 +08:00
