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
hiyouga
e99031daa4
fix inputs
...
Former-commit-id: 446441fdb020b5a102480251cb8536dd8b3f8f99
2024-11-23 18:26:02 +00:00
marko1616
3295519099
Tiny fix.
...
Former-commit-id: 8372c5e3771c42f225d7bd80a758af920f80e893
2024-11-23 16:09:01 +00:00
marko1616
20faaf3418
Support llama3.2vl.
...
Former-commit-id: 3f2c056253c651e8e614c787e2045f4232e82666
2024-11-23 16:07:35 +00:00
hiyouga
d4e0010027
add qwen-coder and opencoder
...
Former-commit-id: 431ac4892cdddba802a02b285031a797e278d0eb
2024-11-15 21:48:38 +08:00
hiyouga
1598e5d355
add image input type
...
Former-commit-id: ffa39ba3db0dbfd375cdf20b9f3cbecd359be1a1
2024-11-04 08:27:20 +00:00
steven
7f7ee0a660
support granite3 models
...
Former-commit-id: 6eefb4d7d25879db42cefae8332ca9db88bff851
2024-11-04 10:35:03 +08:00
hoshi-hiyouga
8c2b7aa1ab
update template
...
Former-commit-id: 478cbb1aa72f218df37b5a4686db2248ad2605dd
2024-11-02 21:21:22 +08:00
hoshi-hiyouga
d99e164cad
Merge branch 'main' into main
...
Former-commit-id: 5f14910910154ba569435e7e68acbd6c30f79e80
2024-11-02 21:20:27 +08:00
hoshi-hiyouga
6f79974e8b
Merge pull request #5910 from Cuiyn/index
...
Support Index series models.
Former-commit-id: c58cc22d06eb1a466ad92601ceb74c9bae6abb51
2024-11-02 20:16:54 +08:00
hiyouga
e83cb17f97
support rank0 logger
...
Former-commit-id: c38aa29336f286266553da4909a7267d7ef21f37
2024-11-02 18:31:04 +08:00
Cuiyn
7806bde8ad
Add support for Index
...
Former-commit-id: a15a69ab4417c6f3273c874cf7ee2c34a5a64141
2024-11-02 13:45:27 +08:00
hoshi-hiyouga
4b2c47fcae
Merge pull request #5909 from hiyouga/hiyouga/dev2
...
[data] support auto convert for single image, add image_dir argument
Former-commit-id: bd08b8c441c47076faa03cc1efde21b22f14f058
2024-11-02 13:43:04 +08:00
hiyouga
ac677205c9
fix #5904
...
Former-commit-id: bfe1abd7afe4595135b568783753d064cb6e0b28
2024-11-02 13:08:15 +08:00
hiyouga
7fa46a24df
fix #5883
...
Former-commit-id: 24da9f59b0bf4874506bbf1ec214f3d5ca43d943
2024-11-02 13:06:34 +08:00
hiyouga
8ecc12ee2a
support multiimage inference
...
Former-commit-id: e80a4819274d46ac9e85db7469dc59d7c4e323c7
2024-11-01 07:25:20 +00:00
hiyouga
1b02915d19
tiny fix
...
Former-commit-id: 0c22da4f1cc710b471f6d511d50ce878521173ca
2024-10-30 08:56:29 +00:00
