hoshi-hiyouga
8265d6a228
Merge pull request #5922 from Tuyohai/main
...
support granite3 models
Former-commit-id: c23a4d0658
2024-12-23 16:46:02 +08:00
hiyouga
47c2d91933
support report custom args
...
Former-commit-id: 5111cac6f8
2024-12-21 21:42:45 +00:00
hiyouga
f07bad7144
fix paligemma infer
...
Former-commit-id: 84cd1188ac
2024-12-21 20:24:32 +00:00
hoshi-hiyouga
547f76e56e
Merge pull request #6401 from Zeyi-Lin/hiyouga/swanlab
...
feat: add swanlab for experiment tracking and visualization.
Former-commit-id: 947e22a4a3
2024-12-21 14:09:33 +08:00
ZeYi Lin
67d4757c35
fix: project blank
...
Former-commit-id: 82e5d75014
2024-12-20 18:26:02 +08:00
ZeYi Lin
cc703b58f5
fix: by hiyouga suggestion
...
Former-commit-id: 3a7ea2048a
2024-12-20 16:43:03 +08:00
ZeYi Lin
8f786ee938
feat: ui improve
...
Former-commit-id: 5f6dafd70e
2024-12-20 11:03:02 +08:00
ZeYi Lin
03dba638e6
fix: text
...
Former-commit-id: 0a52962db3
2024-12-19 21:26:02 +08:00
ZeYi Lin
dd22454fc5
fix: bugs
...
Former-commit-id: d0eb64d5e3
2024-12-19 21:08:16 +08:00
ZeYi Lin
b512a06c3d
docs: config framework
...
Former-commit-id: 7eb49e5ffa
2024-12-19 20:22:36 +08:00
ZeYi Lin
c31933ef9e
fix: string
...
Former-commit-id: 3306919629
2024-12-19 20:18:59 +08:00
hiyouga
8524dcaa4a
fix #6391
...
Former-commit-id: d4c1fda1ad
2024-12-19 12:16:38 +00:00
ZeYi Lin
53103f55b6
feat: optimize frontend
...
Former-commit-id: 8c2df41b93
2024-12-19 19:04:19 +08:00
ZeYi Lin
cc5cde734b
feat: swanlab params
...
Former-commit-id: d5cf87990e
2024-12-19 18:47:27 +08:00
hiyouga
95d3c2620b
support disable shuffling
...
Former-commit-id: c7cedc7569
2024-12-19 08:53:21 +00:00
hiyouga
1a48340680
add swanlab
...
Former-commit-id: 96f8f103e5
2024-12-19 07:12:31 +00:00
hiyouga
92a0d08e27
fix webui
...
Former-commit-id: 369cca8110
2024-12-19 06:48:03 +00:00
hiyouga
433d116080
add paligemma2
...
Former-commit-id: d3509050dc
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: 015f213788
2024-12-18 16:16:17 +08:00
hiyouga
a421113466
support qwen tool format
...
Former-commit-id: 98795854e3
2024-12-17 20:12:06 +00:00
hiyouga
acd62fddb8
change default replace jinja to false
...
Former-commit-id: bcc413cf64
2024-12-17 19:27:10 +00:00
ylfeng
857d23b324
Support Mistral format tools
...
Former-commit-id: 115924af47
2024-12-17 19:13:26 +00:00
hiyouga
f6a2bfc0e8
fix llama3 tool template
...
Former-commit-id: df5655f61c
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: e12c80ace8
2024-12-18 00:13:28 +08:00
hiyouga
a935933bed
support llama3 tool prompt
...
Former-commit-id: b24ae55ebf
2024-12-17 15:52:37 +00:00
Yaser Afshar
76ebd62ac1
Add missing key to init_kwargs
...
Former-commit-id: 1c8ad22a5f
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: 0943776326
2024-12-17 12:25:12 +00:00
zhaohu xing
cfb4c42ae4
support telechat2 model
...
Former-commit-id: 04f19ed0f3
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: 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
hoshi-hiyouga
002c7d2867
Merge pull request #6363 from hiyouga/hiyouga/control_skip_eos
...
[infer] support control eos
Former-commit-id: 6973828307
2024-12-17 19:35:40 +08:00
hiyouga
a94a1eac67
support control eos, fix #6345
...
Former-commit-id: eda76de32b
2024-12-17 10:42:05 +00:00
hiyouga
bff1b94583
generalized packing & fix #6343
...
Former-commit-id: 2d107d3aef
2024-12-17 10:26:19 +00:00
hiyouga
50ca43c3fb
fix #6348
...
Former-commit-id: 142191e466
2024-12-17 10:06:46 +00:00
hiyouga
6f1e450739
fix mrope
...
Former-commit-id: 2811814fc4
2024-12-12 15:08:17 +00:00
hiyouga
cf8cad8e7e
support qwen2vl train proj only
...
Former-commit-id: 99c62660c6
2024-12-05 10:37:42 +00:00
hiyouga
88b06a0c7f
support qwen2vl vllm infer
...
Former-commit-id: 207f8b069c
2024-12-05 10:17:26 +00:00
hiyouga
819f487c8f
fix scripts
...
Former-commit-id: eb3e147d19
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: cf29846830
2024-12-04 22:18:19 +08:00
hoshi-hiyouga
92940817e7
lint
...
Former-commit-id: 6a5074e466
2024-12-04 22:08:27 +08:00
hiyouga
235cdcacee
support batch infer in vllm
...
Former-commit-id: 1324d158f9
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: 263cb82bdb
2024-12-04 18:07:29 +08:00
hiyouga
0ef1dc4dd5
fix vlm zero3 training
...
Former-commit-id: dbb9e5b70e
2024-12-04 09:40:39 +00:00
Azalea
0efa34c9ef
[U] Compute hostname differently
...
Former-commit-id: 6554cdeedb
2024-11-28 22:23:41 -05:00
hiyouga
1c3d86cd65
add qwq
...
Former-commit-id: 68a612115a
2024-11-28 08:50:57 +00:00
Azalea
f5e6e25a1b
[+] Show the hostname
...
Former-commit-id: dfb953b1ad
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: 4424d4de8a
2024-11-27 16:44:42 +08:00
hiyouga
9822cb7bac
fix dataset
...
Former-commit-id: 046b6fb118
2024-11-27 06:27:44 +00:00
hiyouga
d51d96d594
add skywork o1
...
Former-commit-id: ec9ff8caa2
2024-11-27 05:51:59 +00:00
hiyouga
ab3782b0fa
add marco-o1 and openo1 dataset
...
Former-commit-id: 17afb7d410
2024-11-27 04:20:23 +00:00