hiyouga
b58c350c1a
fix #6391
...
Former-commit-id: 067ba6e6cb4d8a1d95bba0a108f73008416a2865
2024-12-19 12:16:38 +00:00
hoshi-hiyouga
10b5193f7d
Merge pull request #6388 from hiyouga/hiyouga/shuffle_control
...
[trainer] support disable shuffling
Former-commit-id: 3243e74a2ed3b1f7fa818842955f91386b591a9c
2024-12-19 17:00:12 +08:00
hiyouga
67479ce5d9
support disable shuffling
...
Former-commit-id: 9d8c35fd6b838ede0bd6827c6c6121f2cba2b11b
2024-12-19 08:53:21 +00:00
hoshi-hiyouga
9c58127f83
Merge pull request #6384 from hiyouga/hiyouga/fix_webui
...
[webui] fix webui args
Former-commit-id: 94294c4e356b3ac5546f897d6e3255ee8c2a260f
2024-12-19 14:57:52 +08:00
hiyouga
573ff59a11
fix webui
...
Former-commit-id: 7152fde4a026e67f15885814c1900f3911d04ee8
2024-12-19 06:48:03 +00:00
hoshi-hiyouga
9445cb63b7
Merge pull request #6379 from hiyouga/hiyouga/add_paligemma2
...
[model] add paligemma2
Former-commit-id: abe3ff3fe0b113e949bf6d2bd10e4c125fb8fe75
2024-12-18 17:03:11 +08:00
hiyouga
abe4bf5cd3
add paligemma2
...
Former-commit-id: dafbc31684cb2566ef23c79e171cdfd02d6d396b
2024-12-18 08:57:26 +00:00
hoshi-hiyouga
98268e25d9
Merge pull request #6313 from ge-xing/main
...
support telechat2 model
Former-commit-id: 282d0619b1047ba48f9bc3ac837d2ed40b7df307
2024-12-18 16:16:17 +08:00
hoshi-hiyouga
dd095c6f97
Merge pull request #6369 from hiyouga/hiyouga/template
...
[template] support qwen2 tool template
Former-commit-id: e1e133635f05f5b83869bc02340d6ea46976f318
2024-12-18 04:23:49 +08:00
hiyouga
99ea353474
support qwen tool format
...
Former-commit-id: cbef4cb501fa1b50fa611e7054a856ce2c5ed10e
2024-12-17 20:12:06 +00:00
hiyouga
fa03756a6a
change default replace jinja to false
...
Former-commit-id: bfe6625f6f6aa294933fa9056a4bfedee4fbe5e2
2024-12-17 19:27:10 +00:00
hoshi-hiyouga
6edc71b9cb
Merge pull request #5473 from AlongWY/mistral
...
Support Mistral format tools
Former-commit-id: 4838427310d49e5942138e4578d2483baa005471
2024-12-18 03:23:24 +08:00
ylfeng
30d61c83c5
Support Mistral format tools
...
Former-commit-id: e42d0e54b7a64a3f017a09e99846d174db7b438f
2024-12-17 19:13:26 +00:00
hoshi-hiyouga
a2a9cf839b
Merge pull request #6368 from hiyouga/hiyouga/fix_llama_template
...
[template] fix llama3 tool template
Former-commit-id: 7c6763c4f3287f758077191361d5b0354741f84a
2024-12-18 01:10:48 +08:00
hiyouga
6ebed2950e
fix llama3 tool template
...
Former-commit-id: 63f28a594a44c011f2e6d418f22ddbfc445db163
2024-12-17 17:05:10 +00:00
hoshi-hiyouga
35741da99b
Merge pull request #6367 from hiyouga/hiyouga/add_model
...
[model&template] add llama3.3 & support llama3 tool prompt
Former-commit-id: c32012c5e4943a30c3061716ed780d6124b6c90d
2024-12-18 00:13:28 +08:00
hiyouga
0335fe54ef
support llama3 tool prompt
...
Former-commit-id: dc45d2f56669fd99935a68cda1ec0e8f36229f7f
2024-12-17 15:52:37 +00:00
hoshi-hiyouga
9a6ed349f1
Merge pull request #5819 from yafshar/remote_code
...
Add trust_remote_code Parameter and Set Default to False
Former-commit-id: e82099350a2fb6d8ddf9c80ba0b18173057d4dcf
2024-12-17 21:10:24 +08:00
Yaser Afshar
eee39dd138
Add missing key to init_kwargs
...
Former-commit-id: 03fc4621dad132164596a58d3e8693787b7e1aca
2024-12-17 12:34:05 +00:00
Yaser Afshar
45596f5ae0
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: 4bf23f406cf5235c16f9f8139850c53354901814
2024-12-17 12:25:12 +00:00
zhaohu xing
1f46c2e5c4
support telechat2 model
...
Former-commit-id: 15a069d85c07842cd28d65845af93c3cf70ef1f4
2024-12-17 12:15:33 +00:00
hoshi-hiyouga
271d642b0c
Merge pull request #6364 from hiyouga/hiyouga/control_reenterent_gc
...
[model] support non-reenterent-gc
Former-commit-id: a8a13cb360980bb4acd493e33ed405e07460fe73
2024-12-17 19:58:36 +08:00
hiyouga
3778edd25d
support non-reenterent-gc & fix #6358
...
Former-commit-id: 20446141e408885eb36d512bfb2dfb62bbc0c20d
2024-12-17 11:41:59 +00:00
hoshi-hiyouga
cf0bd32aae
Merge pull request #6363 from hiyouga/hiyouga/control_skip_eos
...
[infer] support control eos
Former-commit-id: 963640cff370be9f2fab649c88a120a645e6992e
2024-12-17 19:35:40 +08:00
hiyouga
93e266e483
support control eos, fix #6345
...
Former-commit-id: cb0f8399356bf372f3b7963f2565c3d504be0923
2024-12-17 10:42:05 +00:00
hoshi-hiyouga
7e85168d77
Merge pull request #6362 from hiyouga/hiyouga/mllm_packing
...
[model] generalized packing
Former-commit-id: b85f77a2687f7e0d11f7d2e49de54c544e39e3d5
2024-12-17 18:41:48 +08:00
hiyouga
85f185449e
generalized packing & fix #6343
...
Former-commit-id: 3b1e4194616cacd5c24f08b328e31a008bddcf29
2024-12-17 10:26:19 +00:00
hoshi-hiyouga
d959a16684
Merge pull request #6359 from hiyouga/hiyouga/fix_qwen2vl_infer
...
[model] fix qwen2vl infern
Former-commit-id: 419cba5fae31a3c88305fe424b8aae9d59e3941a
2024-12-17 18:15:23 +08:00
hiyouga
90b62807fb
fix #6348
...
Former-commit-id: 83e552320909f4775377889f1512994b7e638a7e
2024-12-17 10:06:46 +00:00
hoshi-hiyouga
0178ea4a41
Merge pull request #6334 from hiyouga/hiyouga/add_examples
...
[assets] update wechat and examples
Former-commit-id: 7725e7ac7d21ad844e8424a920e8bece6f38af19
2024-12-15 01:37:01 +08:00
hiyouga
ea1a17c46c
update assets
...
Former-commit-id: 7b9bd552b2bf97b72976511094eb51dfde5d1017
2024-12-14 17:36:03 +00:00
hiyouga
b57560aa25
fix mrope
...
Former-commit-id: 55bee1d333549ca19858b3f5c1b7b86926e5fb09
2024-12-12 15:08:17 +00:00
hoshi-hiyouga
a26d35ad5e
Merge pull request #6253 from hiyouga/hiyouga/qwen2vl_mm_proj
...
[model] support qwen2vl train proj only
Former-commit-id: 0b0012142ab683da1e0558e6240310bf90f39150
2024-12-05 20:25:33 +08:00
hiyouga
7a7631134f
support qwen2vl train proj only
...
Former-commit-id: 0e949ef03455726e907c6f1039e93ebe480c897a
2024-12-05 10:37:42 +00:00
hoshi-hiyouga
b764758d05
Merge pull request #6251 from hiyouga/hiyouga/vllm_qwen2vl_infer
...
[infer] support qwen2vl vllm infer
Former-commit-id: df76f7d6e124131ce7628c31cce01de4f8e6014c
2024-12-05 18:26:19 +08:00
hiyouga
7f0bd679ac
support qwen2vl vllm infer
...
Former-commit-id: 03ddd2555fb97488cd4daab11e8b672d36150c5a
2024-12-05 10:17:26 +00:00
hoshi-hiyouga
e5135a3356
Merge pull request #6246 from hiyouga/hiyouga/update_examples
...
[examples] update examples
Former-commit-id: ecb688bdb3e940651d64bc1edc85ce4568f3eabe
2024-12-05 16:49:30 +08:00
hiyouga
dc6b9c104f
update examples
...
Former-commit-id: bcb010be7732ae137f156932100ee4d02a93725c
2024-12-05 08:48:25 +00:00
hoshi-hiyouga
a94f6082de
Merge pull request #6242 from hiyouga/hiyouga/fix_script
...
[script] fix scripts
Former-commit-id: cf254ea0891ea2e6522fdbefcccf409ff7aafd99
2024-12-05 11:54:46 +08:00
hiyouga
7695787258
fix scripts
...
Former-commit-id: f94f55d20283298cb7d90d0573992a62df414a8f
2024-12-05 03:47:32 +00:00
hoshi-hiyouga
e5daa53e4c
Merge pull request #6160 from village-way/pr_dataloader
...
fix:tokenized_path not None and load_from_disk return Dataset Trigger…
Former-commit-id: 63de20970c8062aeebed5f366f1675beb12e05bf
2024-12-04 22:18:19 +08:00
hoshi-hiyouga
50782abce6
lint
...
Former-commit-id: 191ccc585399ad4c6c2c4f280b144b2c0a4869f3
2024-12-04 22:08:27 +08:00
hoshi-hiyouga
b83bb3f7fc
Merge pull request #6238 from hiyouga/hiyouga/vllm_batchinfer
...
[infer] feat: support batch infer in vllm
Former-commit-id: 886752801ba8a5bf6fc4853ed618817185950c11
2024-12-04 21:59:13 +08:00
hiyouga
51b18e565d
support batch infer in vllm
...
Former-commit-id: 3ef5ed3b9a44eed2f7e3ff221dfc343d0a97c0b5
2024-12-04 13:50:00 +00:00
hoshi-hiyouga
398634de60
Merge pull request #6190 from JieShenAI/main
...
add vllm_infer script
Former-commit-id: 09c7ea700c83dcf8d75796a1e28a36197f62cab4
2024-12-04 21:19:23 +08:00
hoshi-hiyouga
5902dc82c4
Merge pull request #6170 from hykilpikonna/main
...
[+] Show the hostname in webui title
Former-commit-id: 1cb2f9da317a8db8f45e887ab57cdfdc0e8b9412
2024-12-04 18:07:29 +08:00
hoshi-hiyouga
009628b54e
Merge pull request #6233 from hiyouga/hiyouga/vlm_zero3
...
[data] fix vlm zero3 training
Former-commit-id: b0cbd5e3464a8a1a0f1cf709fb107b23a61f34ff
2024-12-04 17:51:10 +08:00
hiyouga
effad6fbff
fix vlm zero3 training
...
Former-commit-id: 86fe7fe71b51077310357b7b1895522258f9bc7a
2024-12-04 09:40:39 +00:00
JieShen
8880c61217
add async call api
...
Former-commit-id: 0f728386d88cf8253250c6650555d41578114a0c
2024-12-01 22:18:05 +08:00
JieShen
3df16e4323
add vllm_infer script
...
Former-commit-id: 4daab843a3aa096b35e5d3832c01fac4271e4604
2024-11-29 14:22:20 +08:00
