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
1efe525df7
[model] support yarn ( #6693 )
...
Former-commit-id: 1f47b6186c
2025-01-18 13:56:09 +08:00
hoshi-hiyouga
788accb601
fix qwen2 moe ( #6684 )
...
Former-commit-id: 7bf09abf1c
2025-01-17 13:46:09 +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
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
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
fzc8578
08e8499a98
adapt to new mllm_param
...
Former-commit-id: 291384dea8
2025-01-11 00:16:34 +08:00
Zhangchi Feng
d5b18ee4a6
Merge branch 'main' into minicpmv
...
Former-commit-id: ed0895a9c1
2025-01-11 00:01:36 +08:00
hiyouga
c89d17ab63
refactor mllm param logic
...
Former-commit-id: f6f630a1c9
2025-01-10 15:45:48 +00:00
fzc8578
994049380d
fix some
...
Former-commit-id: 15bbcdf8d3
2025-01-10 20:55:52 +08:00
fzc8578
7138b43873
fix some
...
Former-commit-id: 2ee8ba2f39
2025-01-10 20:27:06 +08:00
fzc8578
aeb4f82ef2
tiny fix
...
Former-commit-id: 84026be06e
2025-01-10 20:15:39 +08:00
Zhangchi Feng
f51ac40f0a
Merge branch 'main' into minicpmv
...
Former-commit-id: fc045d7dd8
2025-01-10 20:12:07 +08:00
fzc8578
165fe8e219
add some
...
Former-commit-id: 096a6cb67a
2025-01-10 20:01:22 +08:00
hiyouga
da542fad18
imporve log
...
Former-commit-id: 47e17dd689
2025-01-08 09:56:10 +00:00
fzc8578
b9eeaa9706
add some
...
Former-commit-id: 785cc70ff2
2025-01-06 19:32:39 +08:00
fzc8578
b5ef5059ee
add some
...
Former-commit-id: 79c2d7090c
2025-01-04 11:11:15 +08:00
Yaser Afshar
fe4546a7bb
Add trust_remote_code parameter and remove True
...
- Introduced a new model parameter `trust_remote_code`
- Set the default value of `trust_remote_code` to `False`
to enhance security
Former-commit-id: 0943776326
2024-12-17 12:25:12 +00:00
hoshi-hiyouga
fc18db6290
Merge pull request #6364 from hiyouga/hiyouga/control_reenterent_gc
...
[model] support non-reenterent-gc
Former-commit-id: a665ad6178
2024-12-17 19:58:36 +08:00
hiyouga
64bac4bc7e
support non-reenterent-gc & fix #6358
...
Former-commit-id: f319da6937
2024-12-17 11:41:59 +00:00
hiyouga
bff1b94583
generalized packing & fix #6343
...
Former-commit-id: 2d107d3aef
2024-12-17 10:26:19 +00:00
hiyouga
cf8cad8e7e
support qwen2vl train proj only
...
Former-commit-id: 99c62660c6
2024-12-05 10:37:42 +00:00
hoshi-hiyouga
a489f10986
fix visual patch
...
Former-commit-id: 75b586c31a
2024-11-25 20:06:06 +08:00
hoshi-hiyouga
f48d07cd6c
fix #6136
...
Former-commit-id: 0516e556a7
2024-11-25 19:43:42 +08:00
hiyouga
253752ccca
add forbidden modules
...
Former-commit-id: df477370dc
2024-11-23 18:34:15 +00:00
hiyouga
e99031daa4
fix inputs
...
Former-commit-id: 446441fdb0
2024-11-23 18:26:02 +00:00
marko1616
23fc0c863e
Linter.
...
Former-commit-id: b1e43e56db
2024-11-23 16:09:04 +00:00
marko1616
3295519099
Tiny fix.
...
Former-commit-id: 8372c5e377
2024-11-23 16:09:01 +00:00
hiyouga
e83cb17f97
support rank0 logger
...
Former-commit-id: c38aa29336
2024-11-02 18:31:04 +08:00
hoshi-hiyouga
33e8bfc3ae
Merge pull request #5907 from hiyouga/hiyouga/dev
...
[data] fix template replace behavior
Former-commit-id: 8408339d83
2024-11-02 13:42:53 +08:00
hiyouga
ac677205c9
fix #5904
...
Former-commit-id: bfe1abd7af
2024-11-02 13:08:15 +08:00
hiyouga
3f7c874594
update tests
...
Former-commit-id: 93d3b8f43f
2024-11-02 12:41:44 +08:00
hiyouga
584ce3a105
fix incorrect loss value for vlms
...
Former-commit-id: 30567a1487
2024-10-30 08:56:46 +00:00
hoshi-hiyouga
2179b91acb
Update visual.py
...
Former-commit-id: 0baa7735f6
2024-10-29 22:10:29 +08:00
Kingsley
3053a806e9
Merge branch 'hiyouga:main' into pixtral-patch
...
Former-commit-id: 67f59579d7
2024-10-29 21:01:25 +08:00
hiyouga
0d8aa6e6ef
use pre-commit
...
Former-commit-id: 21db8ed2f4
2024-10-29 09:07:46 +00:00
hiyouga
163cf2ba5c
update requires
...
Former-commit-id: 77666bd227
2024-10-29 16:10:07 +08:00
hoshi-hiyouga
f03b20b267
fix #5797
...
Former-commit-id: b4c7dd3ac5
2024-10-23 20:49:44 +08:00
hoshi-hiyouga
af50c03879
Update loader.py
...
Former-commit-id: 93b9067dfc
2024-10-17 19:48:12 +08:00
Kingsley
8ea1c5c69e
Merge branch 'hiyouga:main' into pixtral-patch
...
Former-commit-id: 95330893c5
2024-10-13 17:42:02 +08:00
huniu20
26e897e861
1. add modelers hub support
...
Former-commit-id: 24ebe187e3
2024-10-09 17:21:37 +08:00
Kingsley
5523a6fd2c
Merge branch 'hiyouga:main' into pixtral-patch
...
Former-commit-id: 93a441a6b7
2024-10-08 21:04:08 +08:00
hiyouga
4464a6ff5b
tiny fix
...
Former-commit-id: 451d271718
2024-10-08 17:48:56 +08:00
