1145 Commits

Author SHA1 Message Date
khazic
21c4a43085 Added specimens for single-card full parameter prediction
Former-commit-id: 47111ce506d2769bfa14b37b729d22b57796b26e
2024-04-13 20:45:19 +08:00
hiyouga
db42378f29 fix #3247
Former-commit-id: d1fb6c72b532bfd4ccd5b19f56708c8391fa53aa
2024-04-12 17:41:33 +08:00
hiyouga
9e7b460b2d fix model card
Former-commit-id: c53a11b6fd477fffb2030a4e3aeb4a56fd21e7a6
2024-04-12 17:11:59 +08:00
hiyouga
c9d3cc181a fix #3238
Former-commit-id: 232642a6215de9b57a1627f39b4efea127948a01
2024-04-12 14:28:11 +08:00
hiyouga
1ae6f0a5f3 Update wechat.jpg
Former-commit-id: f2ba59352e5721ba56590ee8c281e9c71ca57d9b
2024-04-12 14:15:45 +08:00
hiyouga
64c931c0db set dev version
Former-commit-id: 3dfe4cf611a348bf6b4d374044930d5e63535f68
2024-04-11 20:27:34 +08:00
hiyouga
431e9804ee release v0.6.2
Former-commit-id: 9d4c949461d232a959c14859ae7fef191faab711
v0.6.2
2024-04-11 20:08:51 +08:00
hiyouga
797077a46e Merge branch 'main' of https://github.com/hiyouga/LLaMA-Factory
Former-commit-id: 51d0a1a19e9f821cdbf31350dd9ed09193a511ef
2024-04-10 23:58:18 +08:00
hiyouga
d5ca8763ea fix #3225
Former-commit-id: a99f5ed0b6f7932810c6baf127d21f4be44144ad
2024-04-10 23:57:59 +08:00
hoshi-hiyouga
aa5f25b9d2 Merge pull request #3201 from kno10/patch-1 and fix #3200
Pass additional_target to unsloth

Former-commit-id: caf8373c2d6b0ec5bda1345416e02e3324e2e8a4
2024-04-10 00:58:48 +08:00
hoshi-hiyouga
77d16ada1e Update adapter.py
Former-commit-id: 98bc97d8d218182c026e9f57bbcbf40ab1e0bc87
2024-04-10 00:57:51 +08:00
hoshi-hiyouga
e5b4cb62e0 Update adapter.py
Former-commit-id: 2111b586b648caa150a8e41877c7fede75911da8
2024-04-10 00:57:30 +08:00
Erich Schubert
3dccd3c67e Pass additional_target to unsloth
Fixes #3200

Former-commit-id: b5eefe5c4c084b63a12b023cae877fcd1914d4fc
2024-04-09 17:53:40 +02:00
hiyouga
0e08c209c4 fix quant infer and qwen2moe
Former-commit-id: 7f6c2486b83e1d2c96a2314bfa8e1519ca5f574e
2024-04-09 17:12:59 +08:00
hiyouga
3069f37021 tiny fix
Former-commit-id: 9a99fbc86d0be7bd0e6dd1a5475868c32006b08d
2024-04-08 21:28:39 +08:00
hoshi-hiyouga
8682d033eb Merge pull request #3161 from hiyouga/feature/add-mediatek-model
support Breeze-7B

Former-commit-id: 4c6c4a0d8829bc098c202e4c3df36f702d579537
2024-04-08 20:56:51 +08:00
hiyouga
2db3b75057 Merge branch 'main' of https://github.com/hiyouga/LLaMA-Factory
Former-commit-id: 98ad2ccd8f77254bcf7e914eaf09c6b2e6091184
2024-04-08 19:59:24 +08:00
hiyouga
3ab8e313a0 Update wechat.jpg
Former-commit-id: e79e1532fab7b75946b09fefb5c427321c5d5aee
2024-04-08 19:59:07 +08:00
codingma
b5f0ac4c3f add empty line
Former-commit-id: 7b76b4ca08066af0465f138fa756615cbaef32ad
2024-04-07 18:28:08 +08:00
codingma
fecab4d3f1 rename template to breeze
Former-commit-id: 34bdcba0176a1612ab10351e59927ea744c6749c
2024-04-07 18:27:20 +08:00
hoshi-hiyouga
8db8389f1d Merge pull request #3160 from sliderSun/main
support Qwen1.5-32B

Former-commit-id: ff4d313a50e6f3398505e18de0e73afaffe9b77e
2024-04-07 18:00:40 +08:00
codingma
ed14f8bae7 rename template to breeze
Former-commit-id: 5a780e9eec7e8c560d417c1a95afa1be0f878d32
2024-04-07 11:39:54 +08:00
codingma
80aa1f70b6 support https://github.com/hiyouga/LLaMA-Factory/issues/3152
Former-commit-id: 2565a32bd98ef46a3b6e1a5c334093ca46b820d2
2024-04-07 11:34:01 +08:00
sliderSun
7037dcbf38 fix spell error
Former-commit-id: 1d117b7bb6b71ff9ff98b7d5cc0bbf7b879ad385
2024-04-07 10:59:15 +08:00
sliderSun
1fbf190eda support Qwen1.5-32B
Former-commit-id: 21650d467c19c99d30f538f8a70984d4e3417604
2024-04-07 10:56:03 +08:00
sliderSun
09107affda support Qwen1.5-32B
Former-commit-id: 77044d9ef4ce39a038ad769f93569d5eb2f3bfb0
2024-04-07 10:26:13 +08:00
hiyouga
527cce1eb5 update readme
Former-commit-id: a88fe8c1af5e17c2ac459b225a2e03b2cb013783
2024-04-07 00:48:24 +08:00
hiyouga
5dd3c1ab79 update examples
Former-commit-id: b87f8f15194923392d1a1c3d3c617b463cdd8379
2024-04-04 14:48:21 +08:00
hiyouga
51a23c3aaf tiny fix
Former-commit-id: a6d943804b96763dfe85744cf8e6ba8c9ab6cecf
2024-04-04 02:19:03 +08:00
hiyouga
f334b89616 back to gradio 4.21 and fix chat
Former-commit-id: 4b920f24d35c73814b83d56373dd5c913bb57e49
2024-04-04 02:07:20 +08:00
hiyouga
54a4a8217a fix bug in latest gradio
Former-commit-id: 5ddcecda50ccff93d51bebc9ac72c2a0dd483e9b
2024-04-04 00:55:31 +08:00
hiyouga
a6d347726f fix requires for windows
Former-commit-id: 7f6e4126041f2eaa577426310622a115049fbde7
2024-04-03 21:56:43 +08:00
hiyouga
2ecf2bcbf0 fix resize vocab at inference #3022
Former-commit-id: 148bda353f0b53af022c51da9a9e59a56f341510
2024-04-03 18:14:24 +08:00
hiyouga
88d9f47a0b fix #3116
Former-commit-id: ce77d98872fa377fd4bc961701b07982f4b51491
2024-04-03 14:47:59 +08:00
hiyouga
42ccb9b073 Update wechat.jpg
Former-commit-id: f0a9245c7e47e0ed15084f12f0fb35e501201496
2024-04-03 14:42:21 +08:00
hiyouga
4b23159f53 update vllm example
Former-commit-id: 49a2dfaf90982079239d116fcfac9ca72a8fc2b5
2024-04-02 22:45:20 +08:00
hiyouga
3b16f97c6c update readme
Former-commit-id: 66b0fe4e964ad4d882935910f5e512666c54c2b2
2024-04-02 22:17:48 +08:00
hiyouga
86513f28dc update examples
Former-commit-id: fc7f1cc365ee481b76f9c7e6f1947b49cf131fbf
2024-04-02 21:09:25 +08:00
hiyouga
03c538ebb3 add zh readme
Former-commit-id: 7765f337c7f0d7b8866beecb990c346700146c67
2024-04-02 20:58:45 +08:00
hiyouga
e341fa59fe update examples
Former-commit-id: f22eaeb5bc5329146feb0cc5455fae8ce10380f8
2024-04-02 20:51:21 +08:00
hiyouga
9df316931b update examples
Former-commit-id: 31ffbde24dd2e30c3d06331ac4b47d966fc2a191
2024-04-02 20:41:49 +08:00
hiyouga
135c4e3512 update readme
Former-commit-id: 11a6c1bad65a86b0f3d9c5e5df84d246d7d368df
2024-04-02 20:37:37 +08:00
hiyouga
291ac11156 update readme
Former-commit-id: 949e5fe63811afb05cc687a2117295d494979b69
2024-04-02 20:22:11 +08:00
hiyouga
bf5ffeeae0 simplify readme
Former-commit-id: 92dab8a90bdd82a72a06559943467b56dde12c71
2024-04-02 20:07:43 +08:00
hiyouga
f4be51f356 add moe aux loss control #3085
Former-commit-id: b267aeb53fc49d2eeb0f3fc5ebe55e643f5db377
2024-04-02 14:26:31 +08:00
hiyouga
c7104f8fab fix #3022
Former-commit-id: 9ddbe2866a4a4433d7635659a5635d16c59800b1
2024-04-02 13:58:39 +08:00
hiyouga
bc3ced05b8 Update SECURITY.md
Former-commit-id: a86ae1724114fe9634d8a80f9cccdc948f7766e4
2024-04-01 23:30:03 +08:00
hiyouga
ab6476a9a4 set dev version
Former-commit-id: dd73a0c2489a69e32afc2131407ee62be7779d8b
2024-04-01 23:24:08 +08:00
hiyouga
829cf6458a fix #3083
Former-commit-id: 4a6ca621c09d179561acc5957c8c911a4e44184c
2024-04-01 22:53:52 +08:00
hiyouga
8d987b7af7 add qwen1.5 moe
Former-commit-id: 54b7d349088a828d32551fde56b3467a82df1b9b
2024-04-01 21:49:40 +08:00