170 Commits

Author SHA1 Message Date
hoshi-hiyouga
ff8ef6f52c [model] fix mllama any image (#6637)
* fix mllama any image

* reorder classes

Former-commit-id: 1242a1c4b4a465c06363fdc59302e80e5c4c96e6
2025-01-14 16:47:58 +08:00
Zhangchi Feng
429a027832 Support new features of MiniCPM-V (#6626)
* fix template name

* tiny fix

* support minicpm-o-2.6

Former-commit-id: 53034a61c7654358f46916cbc370910fb2aeff3b
2025-01-14 00:26:19 +08:00
hoshi-hiyouga
7ab274eb67 [inference] fix stop token for object detection (#6624)
* fix stop token

* update minicpm data pipeline

* fix npu qlora examples

Former-commit-id: 844919fadaa8a61dfae47020971ea80730b2346f
2025-01-13 21:34:20 +08:00
Zhangchi Feng
d1437aefe0 Fix template name of MiniCPM-V (#6620)
* fix template name

* tiny fix

Former-commit-id: 94dea52cef709a7e6f1cdc0b78e83e0422bd65d3
2025-01-13 16:46:48 +08:00
fzc8578
9ab1d4fb3c fix system prompt and tests
Former-commit-id: 955efca677b299749f3d40d587ee310951537543
2025-01-13 14:18:06 +08:00
Zhangchi Feng
a53daaf821 Merge branch 'main' into minicpmv
Former-commit-id: 8a9c90759feda975faadc5858bd44b7ea116e7fb
2025-01-11 00:01:36 +08:00
hiyouga
e49c021e22 refactor mllm param logic
Former-commit-id: b895c190945cf5d991cb4e4dea2ae73cc9c8d246
2025-01-10 15:45:48 +00:00
fzc8578
3a8f989faa fix some
Former-commit-id: cd5a1a8b9c6eb59d6e95f79573f60ad8668f1942
2025-01-10 20:27:06 +08:00
Zhangchi Feng
e838fcdd48 Merge branch 'main' into minicpmv
Former-commit-id: d8840ae416660e23f1d615ffd404f519360151d9
2025-01-10 20:12:07 +08:00
hiyouga
edba9b534f improve template, add phi4 model
Former-commit-id: a785b6796e445a3adba45c5b6947166a2ff99871
2025-01-09 18:27:54 +00:00
hiyouga
760dea0787 imporve log
Former-commit-id: a6abf375975ffea3d51e1b944c9855b5f62ffac8
2025-01-08 09:56:10 +00:00
fzc8578
8f97891153 add some
Former-commit-id: 81176fe226da89eace89cb202bad68e73b7c2a02
2025-01-04 11:11:15 +08:00
hiyouga
0b20167b61 add deepseek3 model
Former-commit-id: 611779d412f31e25b1ed38049050eee2da61dde5
2024-12-30 13:39:20 +00:00
hoshi-hiyouga
68e11c59fd Merge pull request #5507 from piamo/main
Add deepseek-v2.5 template

Former-commit-id: 8a4911d201e219465fe0835a3ceb967f8b80dc0e
2024-12-30 21:08:25 +08:00
hiyouga
a64d93ed28 update readme
Former-commit-id: 1deda4750e0df6c46aeb33cf3f8b35baa537cc1d
2024-12-23 14:08:59 +00:00
hoshi-hiyouga
3f842b4cd0 Merge pull request #5922 from Tuyohai/main
support granite3 models

Former-commit-id: a9087bc0549f7f16e5b4c39e324043755b1618c8
2024-12-23 16:46:02 +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
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
ylfeng
30d61c83c5 Support Mistral format tools
Former-commit-id: e42d0e54b7a64a3f017a09e99846d174db7b438f
2024-12-17 19:13:26 +00:00
hiyouga
6ebed2950e fix llama3 tool template
Former-commit-id: 63f28a594a44c011f2e6d418f22ddbfc445db163
2024-12-17 17:05:10 +00:00
hiyouga
0335fe54ef support llama3 tool prompt
Former-commit-id: dc45d2f56669fd99935a68cda1ec0e8f36229f7f
2024-12-17 15:52:37 +00:00
zhaohu xing
1f46c2e5c4 support telechat2 model
Former-commit-id: 15a069d85c07842cd28d65845af93c3cf70ef1f4
2024-12-17 12:15:33 +00:00
hiyouga
c672520e37 fix dataset
Former-commit-id: d4a2d299414984a4043d30034c5c95e2d717a49e
2024-11-27 06:27:44 +00:00
hiyouga
d20bfe6f7b add skywork o1
Former-commit-id: 272a6fe972de926e5841c1570995f4e6fed9f28d
2024-11-27 05:51:59 +00:00
hiyouga
7631b97e80 add marco-o1 and openo1 dataset
Former-commit-id: 51d49e075470951f109bcdde136203f972450c2e
2024-11-27 04:20:23 +00:00
hiyouga
cc22c045a7 fix inputs
Former-commit-id: 7d535bb8cdf7e81edda81152e63c8cfe6c9dcc9f
2024-11-23 18:26:02 +00:00
marko1616
a948755f28 Support llama3.2vl.
Former-commit-id: 664229d7d1f7994e1ae68c5d197ab81f081bcd2e
2024-11-23 16:07:35 +00:00
hiyouga
a08f57cae8 add qwen-coder and opencoder
Former-commit-id: 9669a42704cd40bdfc76ca278cc6a562549bc27d
2024-11-15 21:48:38 +08:00
steven
4a5294554b support granite3 models
Former-commit-id: 8cff612e55eb7df116e51c4dd21e7a42543e7a1f
2024-11-04 10:35:03 +08:00
hoshi-hiyouga
c7be25fbfb update template
Former-commit-id: 3559ef6115a831dcd1adf7210995ffd62890cff6
2024-11-02 21:21:22 +08:00
hoshi-hiyouga
e02cdaa4aa Merge branch 'main' into main
Former-commit-id: 154f504fc2cebaae2b58c0121d6d8d8016db1bb2
2024-11-02 21:20:27 +08:00
hoshi-hiyouga
f2cf5d5b6d Merge pull request #5910 from Cuiyn/index
Support Index series models.

Former-commit-id: b74d9fa8efeb4f52ba0e20538ad90c8b40492e29
2024-11-02 20:16:54 +08:00
hiyouga
a117731ecb support rank0 logger
Former-commit-id: 84528eabe560091bfd866b6a0ca864085af7529b
2024-11-02 18:31:04 +08:00
Cuiyn
66d235eacc Add support for Index
Former-commit-id: 4e6dba16ca1755235d2ae117b53b68c5ae2f239a
2024-11-02 13:45:27 +08:00
hiyouga
2a92af3089 fix #5904
Former-commit-id: 079ebe038b11f36a11681dc8688f8ea48bccf324
2024-11-02 13:08:15 +08:00
hiyouga
4329e5d4d8 tiny fix
Former-commit-id: b8f4b145506851cf5488cd8551a04d1c7603019b
2024-10-30 08:56:29 +00:00
hoshi-hiyouga
3cd47b8077 Update template.py
Former-commit-id: 99a01547ca31adade1c48feae5796e06b73d387c
2024-10-29 22:11:21 +08:00
Kingsley
e62a1f4947 Merge branch 'hiyouga:main' into pixtral-patch
Former-commit-id: 438302edfdb66b6397266b8b17ac66f60a89300c
2024-10-29 21:01:25 +08:00
hiyouga
dbbfb5f5dc use pre-commit
Former-commit-id: 7cfede95df22a9ff236788f04159b6b16b8d04bb
2024-10-29 09:07:46 +00:00
KUANGDD
ff67d4117f modify style & little change
Former-commit-id: c988477d14dc656450d5fec31895781b7f9f7dce
2024-10-23 15:24:07 +08:00
Kingsley
9d06d21a40 Merge branch 'hiyouga:main' into pixtral-patch
Former-commit-id: 2076d00dfbe1279a91207157fd6d9a118427626a
2024-10-08 21:04:08 +08:00
hiyouga
aa22bf217f tiny fix
Former-commit-id: d8ddd07c2ed14d871fb25743c20265fc99e3e221
2024-10-08 17:48:56 +08:00
Kingsley
cf3c0afa93 Merge branch 'hiyouga:main' into pixtral-patch
Former-commit-id: df0baeaa3fd093433d92b7921d3a57d88061d6d4
2024-09-30 19:33:29 +08:00
hoshi-hiyouga
71658f4f55 Update template.py
Former-commit-id: d893289b595c0530b5aeb8902369885118809b86
2024-09-30 16:39:48 +08:00
Zhangchi Feng
b3306c0876 Merge branch 'main' into pixtral-patch
Former-commit-id: 0cf52d48fbc505e2fba29e5df0f2e6722db7ac79
2024-09-30 12:37:03 +08:00
shing100
ff9e5dd65c fix chat template Exaone3.0
Former-commit-id: 2e32864b59c1ef1a78f3eb1c28fbf578cfaa19cd
2024-09-30 09:44:21 +09:00
shing100
221cc308f3 add Exaone3.0 template
Former-commit-id: f7478af1d04353ab13236323e3bfb96fd2870fce
2024-09-30 09:18:25 +09:00
BUAADreamer
e7e3e1901b fix template
Former-commit-id: cfd05bb009895a936c59f3d97afebf2ed8006f84
2024-09-29 22:56:36 +08:00