Commit Graph

2578 Commits

Author SHA1 Message Date
codingma
03de5ac912 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>
2025-01-13 19:43:36 +08:00
Zhangchi Feng
3077f20339 Fix template name of MiniCPM-V (#6620)
* fix template name

* tiny fix
2025-01-13 16:46:48 +08:00
hoshi-hiyouga
6eec50c74d Merge pull request #6598 from BUAADreamer/minicpmv
[model] Support MiniCPM-V
2025-01-13 15:24:02 +08:00
fzc8578
a019cece80 remove tests 2025-01-13 15:08:35 +08:00
fzc8578
c2fa4cc7b1 fix tests 2025-01-13 15:01:39 +08:00
fzc8578
0cc7260a93 fix style 2025-01-13 14:19:38 +08:00
fzc8578
cfaa8e4890 fix system prompt and tests 2025-01-13 14:18:06 +08:00
fzc8578
01e9cfd406 add some 2025-01-11 15:03:20 +08:00
fzc8578
10073319b4 add cpm_o test 2025-01-11 11:55:30 +08:00
fzc8578
c506f763df add cpm_o test 2025-01-11 11:49:03 +08:00
fzc8578
7b44f3127e fix format 2025-01-11 01:27:40 +08:00
fzc8578
a650e114e9 add some 2025-01-11 01:10:24 +08:00
fzc8578
291384dea8 adapt to new mllm_param 2025-01-11 00:16:34 +08:00
Zhangchi Feng
ed0895a9c1 Merge branch 'main' into minicpmv 2025-01-11 00:01:36 +08:00
hoshi-hiyouga
382e932228 Merge pull request #6600 from hiyouga/hiyouga/refactor_mllm_param
[model] refactor mllm param logic
2025-01-10 23:53:37 +08:00
hiyouga
f6f630a1c9 refactor mllm param logic 2025-01-10 15:45:48 +00:00
fzc8578
e45329e745 add minicpmv2.6 2025-01-10 23:45:44 +08:00
fzc8578
771cc80294 add some 2025-01-10 23:29:06 +08:00
fzc8578
ae1f528df3 add some 2025-01-10 21:25:32 +08:00
fzc8578
15bbcdf8d3 fix some 2025-01-10 20:55:52 +08:00
fzc8578
d09032049c fix version 2025-01-10 20:31:04 +08:00
fzc8578
2ee8ba2f39 fix some 2025-01-10 20:27:06 +08:00
fzc8578
84026be06e tiny fix 2025-01-10 20:15:39 +08:00
Zhangchi Feng
fc045d7dd8 Merge branch 'main' into minicpmv 2025-01-10 20:12:07 +08:00
fzc8578
096a6cb67a add some 2025-01-10 20:01:22 +08:00
hoshi-hiyouga
b308ddf097 Merge pull request #6597 from hiyouga/hiyouga/upd_wechat
[assets] update wechat
2025-01-10 18:41:47 +08:00
hiyouga
70ed03b288 update wechat 2025-01-10 10:40:25 +00:00
hoshi-hiyouga
5ffd8ad192 Merge pull request #6588 from hiyouga/hiyouga/upd_issue_temp
[gh] update issue template
2025-01-10 03:03:48 +08:00
hiyouga
aa8d0a223b update issue template 2025-01-09 18:58:53 +00:00
hoshi-hiyouga
8b209cb49d Merge pull request #6585 from hiyouga/hiyouga/add_phi4
[model] add phi4 model
2025-01-10 02:39:17 +08:00
hiyouga
ae16ea755d improve template, add phi4 model 2025-01-09 18:27:54 +00:00
hoshi-hiyouga
6b34b69fa6 Merge pull request #6564 from stephen-nju/fix_ray
Fix ray
2025-01-08 18:14:18 +08:00
hoshi-hiyouga
18431527ba Merge pull request #6565 from hiyouga/hiyouga/improve_log
[misc] imporve log
2025-01-08 18:08:21 +08:00
zhubin
9c4c84828b fix –get ray args when args not a dict 2025-01-08 10:06:02 +00:00
hiyouga
47e17dd689 imporve log 2025-01-08 09:56:10 +00:00
hoshi-hiyouga
d23a98825b Merge pull request #6542 from erictang000/et/ray-integration
Ray Train integration with LLaMA-Factory
2025-01-08 11:46:03 +08:00
hiyouga
c46675d5e5 fix llamaboard with ray 2025-01-07 09:59:24 +00:00
hiyouga
d8cac6f546 refactor ray integration, support save ckpt 2025-01-07 09:39:10 +00:00
Eric Tang
1e8e7be0a5 run style check 2025-01-07 08:55:44 +00:00
Kourosh Hakhamaneshi
163ddb680b drafting ray integration
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
2025-01-07 08:55:44 +00:00
hoshi-hiyouga
c973f32849 Merge pull request #6547 from hiyouga/hiyouga/fix_pixtral_dpo
[trainer] fix pixtral dpo
2025-01-07 14:38:55 +08:00
hiyouga
870f23d7ea fix #6546 2025-01-07 06:30:44 +00:00
fzc8578
785cc70ff2 add some 2025-01-06 19:32:39 +08:00
hoshi-hiyouga
b832ed9a60 Merge pull request #6528 from hiyouga/hiyouga/upd_wechat
[assets] update wechat
2025-01-04 16:01:21 +08:00
hiyouga
cd14336506 update wechat 2025-01-04 07:59:57 +00:00
Zhangchi Feng
ab87bd6b13 Merge branch 'hiyouga:main' into minicpmv 2025-01-04 11:20:33 +08:00
fzc8578
79c2d7090c add some 2025-01-04 11:11:15 +08:00
hoshi-hiyouga
e6d603ac37 Merge pull request #6524 from hiyouga/hiyouga/upd_scripts
[misc] update scripts
2025-01-03 23:52:26 +08:00
hiyouga
dd44c65d7f update scripts 2025-01-03 10:50:32 +00:00
hoshi-hiyouga
51ef90ce0a Merge pull request #6515 from hiyouga/hiyouga/misc
[misc] update model name
2025-01-02 20:20:02 +08:00