264 Commits

Author SHA1 Message Date
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
Zhangchi Feng
d5b18ee4a6 Merge branch 'main' into minicpmv
Former-commit-id: ed0895a9c13b0ea8a5cace6b060f01d9771816ad
2025-01-11 00:01:36 +08:00
hiyouga
c89d17ab63 refactor mllm param logic
Former-commit-id: f6f630a1c96514053176abb12e35a06242e62abd
2025-01-10 15:45:48 +00:00
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
994049380d fix some
Former-commit-id: 15bbcdf8d3265f4154d3937719da5e54a5963355
2025-01-10 20:55:52 +08:00
fzc8578
7138b43873 fix some
Former-commit-id: 2ee8ba2f390551af1b865cfa813f5c8b7bbb41c5
2025-01-10 20:27:06 +08:00
Zhangchi Feng
f51ac40f0a Merge branch 'main' into minicpmv
Former-commit-id: fc045d7dd871985d621430b5662cba882188a59c
2025-01-10 20:12:07 +08:00
fzc8578
165fe8e219 add some
Former-commit-id: 096a6cb67a7dfd14a6e339d96baab78c12d36a87
2025-01-10 20:01:22 +08:00
hiyouga
b471def13d improve template, add phi4 model
Former-commit-id: ae16ea755d581a5a288fb55f12481215f369b255
2025-01-09 18:27:54 +00:00
hiyouga
da542fad18 imporve log
Former-commit-id: 47e17dd689840ca9b3c5f34448e5f80265336cca
2025-01-08 09:56:10 +00:00
fzc8578
b9eeaa9706 add some
Former-commit-id: 785cc70ff205f5962c3ca67f453589e4a471ba8c
2025-01-06 19:32:39 +08:00
Zhangchi Feng
a0188a430f Merge branch 'hiyouga:main' into minicpmv
Former-commit-id: ab87bd6b1398b379b1a7a95f01a6539743b9db2d
2025-01-04 11:20:33 +08:00
fzc8578
b5ef5059ee add some
Former-commit-id: 79c2d7090cbf364063ea3608814ab18aa27fdc87
2025-01-04 11:11:15 +08:00
hiyouga
da8721a70e fix #6499
Former-commit-id: 1800f8c72dfa618c71c84a3a18ecdef4d82754f7
2025-01-02 11:28:54 +00:00
hiyouga
d0e729cd33 add deepseek3 model
Former-commit-id: e67b9dcc3ad0c003bc3afd7601ecd2adfbf9666b
2024-12-30 13:39:20 +00:00
hoshi-hiyouga
1178cb0e33 Merge pull request #5507 from piamo/main
Add deepseek-v2.5 template

Former-commit-id: 91467ed313802ac3950c2e11a7d0997a36bcbddd
2024-12-30 21:08:25 +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
353259f03f update readme
Former-commit-id: 8fd38d273e5bc3b28a4741b230010fece87e7070
2024-12-23 14:08:59 +00:00
hoshi-hiyouga
8265d6a228 Merge pull request #5922 from Tuyohai/main
support granite3 models

Former-commit-id: c23a4d0658323434c386716c25855711202e37a9
2024-12-23 16:46:02 +08:00
hiyouga
433d116080 add paligemma2
Former-commit-id: d3509050dc4d3105a6e62acc9a1ba481269279a2
2024-12-18 08:57:26 +00:00
hoshi-hiyouga
d43080b534 Merge pull request #6313 from ge-xing/main
support telechat2 model

Former-commit-id: 015f2137887bb9f27fcb0d6cc67ef729aad4031e
2024-12-18 16:16:17 +08:00
hiyouga
a421113466 support qwen tool format
Former-commit-id: 98795854e3fda7b0c0bc209b3e2496b0036e154e
2024-12-17 20:12:06 +00:00
hiyouga
acd62fddb8 change default replace jinja to false
Former-commit-id: bcc413cf64cbee068e2f19475ce7919c65284489
2024-12-17 19:27:10 +00:00
ylfeng
857d23b324 Support Mistral format tools
Former-commit-id: 115924af47496daa747a018952b6a32ccbd9cecb
2024-12-17 19:13:26 +00:00
hiyouga
f6a2bfc0e8 fix llama3 tool template
Former-commit-id: df5655f61cb847dc2d9eb7b34266b20343ff90d6
2024-12-17 17:05:10 +00:00
hoshi-hiyouga
1cc24ed206 Merge pull request #6367 from hiyouga/hiyouga/add_model
[model&template] add llama3.3 & support llama3 tool prompt

Former-commit-id: e12c80ace8b59a9556ee40f5b810f233f9b8174a
2024-12-18 00:13:28 +08:00
hiyouga
a935933bed support llama3 tool prompt
Former-commit-id: b24ae55ebf548db904a9fe1876192024d8a96108
2024-12-17 15:52:37 +00:00
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: 09437763267bc7081159a6878cee9652a2b1ddac
2024-12-17 12:25:12 +00:00
zhaohu xing
cfb4c42ae4 support telechat2 model
Former-commit-id: 04f19ed0f36e691d89ccb7ac19bae70c59640aaa
2024-12-17 12:15:33 +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
88b06a0c7f support qwen2vl vllm infer
Former-commit-id: 207f8b069ca35a28de4588b4962e7254f451c52c
2024-12-05 10:17:26 +00:00
hiyouga
819f487c8f fix scripts
Former-commit-id: eb3e147d198a3ecb02c65f7733cec7cd9d3814a3
2024-12-05 03:47:32 +00:00
hoshi-hiyouga
9bbeba6323 Merge pull request #6160 from village-way/pr_dataloader
fix:tokenized_path not None and load_from_disk return Dataset Trigger…
Former-commit-id: cf298468309cd923d830dcaf7a1aa837519faf1e
2024-12-04 22:18:19 +08:00
hoshi-hiyouga
92940817e7 lint
Former-commit-id: 6a5074e46695378b76d58aac8ad7768b6b034b9c
2024-12-04 22:08:27 +08:00
hiyouga
0ef1dc4dd5 fix vlm zero3 training
Former-commit-id: dbb9e5b70efab37ed057b2d5822b9d0d23e99fb1
2024-12-04 09:40:39 +00:00
wangdepeng
ae09c6c214 fix:tokenized_path not None and load_from_disk return Dataset Trigger stuck
Former-commit-id: 4424d4de8aca0e4d3b92672584978f3cc3fc33da
2024-11-27 16:44:42 +08:00
hiyouga
9822cb7bac fix dataset
Former-commit-id: 046b6fb118e3ea75062c6a759720a1759639e93c
2024-11-27 06:27:44 +00:00
hiyouga
d51d96d594 add skywork o1
Former-commit-id: ec9ff8caa2637965d41937cce7de4e4d51d054eb
2024-11-27 05:51:59 +00:00
hiyouga
ab3782b0fa add marco-o1 and openo1 dataset
Former-commit-id: 17afb7d4103499a9a090a6624896cfa123e9e1d6
2024-11-27 04:20:23 +00:00
hoshi-hiyouga
6cd90efb82 Merge pull request #6152 from hiyouga/hiyouga/add_num_proc_in_data_load
[data] add num_proc in load_dataset

Former-commit-id: b26c490ac3a0a8a6342f940eb6ccb7b8b6d78f93
2024-11-27 00:16:15 +08:00
hiyouga
358708ee97 fix #6149
Former-commit-id: 362d579ce83e63007e6f89f264d06d2698671cc6
2024-11-26 16:03:02 +00:00
hiyouga
006022cadd fix mllama cross_mask
Former-commit-id: 598c22e43f3f10a335933339cc612744c4835eb0
2024-11-26 15:56:58 +00:00
hoshi-hiyouga
118ffe50e3 lint
Former-commit-id: da9e4ddd26ebd6e7eb266aa0bef7505465a6b119
2024-11-25 22:55:56 +08:00
hoshi-hiyouga
c0ffe68745 fix #6139
Former-commit-id: d87e16cf5c46dadbfcda7b8ac8edfef6a012f97f
2024-11-25 22:22:06 +08:00
hiyouga
65699c29d4 fix vllm
Former-commit-id: 13ee1f5cec815590c5d290f0aca264e6d16ddd5d
2024-11-25 00:07:24 +08:00