ZeYi Lin
67d4757c35
fix: project blank
...
Former-commit-id: 82e5d75014ffe5fbe762711adecf59c94ab29f59
2024-12-20 18:26:02 +08:00
ZeYi Lin
cc703b58f5
fix: by hiyouga suggestion
...
Former-commit-id: 3a7ea2048a41eafc41fdca944e142f5a0f35a5b3
2024-12-20 16:43:03 +08:00
ZeYi Lin
8f786ee938
feat: ui improve
...
Former-commit-id: 5f6dafd70e962b8fe9a294d555133002135f80df
2024-12-20 11:03:02 +08:00
ZeYi Lin
03dba638e6
fix: text
...
Former-commit-id: 0a52962db365e7456c858a8e58c19313f19d1e09
2024-12-19 21:26:02 +08:00
ZeYi Lin
dd22454fc5
fix: bugs
...
Former-commit-id: d0eb64d5e3472a166c9adac4cb4ba06bdd663e46
2024-12-19 21:08:16 +08:00
ZeYi Lin
b512a06c3d
docs: config framework
...
Former-commit-id: 7eb49e5ffaea59d8a2756ae7ff55bd57b9077f4b
2024-12-19 20:22:36 +08:00
ZeYi Lin
c31933ef9e
fix: string
...
Former-commit-id: 330691962960fdd2053236e43a919e8f15e2bf27
2024-12-19 20:18:59 +08:00
hiyouga
8524dcaa4a
fix #6391
...
Former-commit-id: d4c1fda1ad19e73484d8d51d81e490cdb8781955
2024-12-19 12:16:38 +00:00
ZeYi Lin
53103f55b6
feat: optimize frontend
...
Former-commit-id: 8c2df41b937f491f7ebf593b20c65a19738c7642
2024-12-19 19:04:19 +08:00
ZeYi Lin
cc5cde734b
feat: swanlab params
...
Former-commit-id: d5cf87990e5bea920ecd1561def09fa17cf328b1
2024-12-19 18:47:27 +08:00
hiyouga
95d3c2620b
support disable shuffling
...
Former-commit-id: c7cedc7569973a2879c689637b2923e8b26f1a81
2024-12-19 08:53:21 +00:00
hiyouga
1a48340680
add swanlab
...
Former-commit-id: 96f8f103e58a8ff307b0ce36c967de04f452434a
2024-12-19 07:12:31 +00:00
hiyouga
92a0d08e27
fix webui
...
Former-commit-id: 369cca8110e6923ad9978b6b93928a3bcb5c6f30
2024-12-19 06:48:03 +00:00
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
76ebd62ac1
Add missing key to init_kwargs
...
Former-commit-id: 1c8ad22a5f167bf4e1c845e273583e5cb3a0214e
2024-12-17 12:34:05 +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
hoshi-hiyouga
fc18db6290
Merge pull request #6364 from hiyouga/hiyouga/control_reenterent_gc
...
[model] support non-reenterent-gc
Former-commit-id: a665ad6178516faf8aaa628d3b2c672ad831d7b7
2024-12-17 19:58:36 +08:00
hiyouga
64bac4bc7e
support non-reenterent-gc & fix #6358
...
Former-commit-id: f319da6937964c5068864f7815efbf3847bd4ad8
2024-12-17 11:41:59 +00:00
hoshi-hiyouga
002c7d2867
Merge pull request #6363 from hiyouga/hiyouga/control_skip_eos
...
[infer] support control eos
Former-commit-id: 69738283071567eeecb492ac38ce1df3b994d975
2024-12-17 19:35:40 +08:00
hiyouga
a94a1eac67
support control eos, fix #6345
...
Former-commit-id: eda76de32bab103c650f246327d214539ae6f291
2024-12-17 10:42:05 +00:00
hiyouga
bff1b94583
generalized packing & fix #6343
...
Former-commit-id: 2d107d3aefd5af61163056634c8b91fe3cb3e77c
2024-12-17 10:26:19 +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
cf8cad8e7e
support qwen2vl train proj only
...
Former-commit-id: 99c62660c67fd2567c094bb49ec7d108e5670730
2024-12-05 10:37:42 +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
235cdcacee
support batch infer in vllm
...
Former-commit-id: 1324d158f954d777f1fbf09f46149c372704b388
2024-12-04 13:50:00 +00:00
hoshi-hiyouga
ed4c4bab49
Merge pull request #6170 from hykilpikonna/main
...
[+] Show the hostname in webui title
Former-commit-id: 263cb82bdb3dfb0c213018f25022686a3dab617e
2024-12-04 18:07:29 +08:00
hiyouga
0ef1dc4dd5
fix vlm zero3 training
...
Former-commit-id: dbb9e5b70efab37ed057b2d5822b9d0d23e99fb1
2024-12-04 09:40:39 +00:00
Azalea
0efa34c9ef
[U] Compute hostname differently
...
Former-commit-id: 6554cdeedb8ab669ce500be404dab8d42a90779b
2024-11-28 22:23:41 -05:00
hiyouga
1c3d86cd65
add qwq
...
Former-commit-id: 68a612115aebba51695d22be4397c16c86f3b40a
2024-11-28 08:50:57 +00:00
Azalea
f5e6e25a1b
[+] Show the hostname
...
Former-commit-id: dfb953b1adb79ed9f886ecac6851a559617aaa5a
2024-11-28 12:25:02 +08:00
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
