2030 Commits

Author SHA1 Message Date
hoshi-hiyouga
d3a1d6a8a5 Merge pull request #5163 from liu-zichen/fix_ppo_optim
fix lr not change

Former-commit-id: f3c03ec6a89bf57f290820fa31eda24291355e4e
2024-08-19 23:56:24 +08:00
hoshi-hiyouga
a2de4a501a Merge pull request #5185 from chenhuiyu/feature/add-sailorllm-template
Add SailorLLM template

Former-commit-id: 28387d6b2f9e3bcc6321345c46b525c8180ebf7e
2024-08-19 23:51:49 +08:00
hoshi-hiyouga
062e74cbed Merge pull request #5188 from Zxilly/main
fix: report correct device count for intel xpu
Former-commit-id: cd3c536cb3936061d905256850b0e57df4498010
2024-08-19 23:51:39 +08:00
hoshi-hiyouga
4b95d55bd8 Merge pull request #5193 from Ricardo-L-C/main
_is_bf16_available judgment supports npu

Former-commit-id: 18b9ac49c45af773a2ea563f5e1852dc4b775db8
2024-08-19 23:40:59 +08:00
hoshi-hiyouga
eb7a2557e7 Update template.py
Former-commit-id: c6822a217e1c296f4aedd9a2c7610acd1dbd443e
2024-08-19 23:40:16 +08:00
hiyouga
ef705788c6 update readme
Former-commit-id: 756e438866876fa54495cf557dd1e299b17a42fb
2024-08-19 23:32:04 +08:00
Ricardo
d2bb1c2041 _is_bf16_available judgment supports npu
Former-commit-id: 50a1e892a1005b4cdd82dca1005f71db08ed89a2
2024-08-16 02:58:22 +00:00
Zxilly
b31a2da778 fix: report correct device count for intel xpu
Former-commit-id: 0618f660b6511599365bd9be64499dbab41a79ba
2024-08-15 08:30:43 +00:00
Huiyu Chen
649a5d55ec Add SailorLLM template
Former-commit-id: a594abe0321a718394a97b5a48ded16e2012c1f0
2024-08-15 15:10:14 +08:00
liu-zichen
bc6583610c fix lr not change
Former-commit-id: 387dd2d51b5d8cd666459040fdd16525b34720d9
2024-08-13 16:33:34 +08:00
codingma
c76f06d76a add tutorial and doc links
Former-commit-id: 4f6072562a34e0ec97471210ff54244cf0d0f3df
2024-08-13 16:13:10 +08:00
“Wzw”
db93661225 fix Llama-template's system prompt bug
Former-commit-id: 2e3eddcd0918b0c968ded0df7c82e3dcff870381
2024-08-12 19:22:12 +08:00
hiyouga
eb50a8092d update readme
Former-commit-id: 4fecc5ee56873a7ab4941e46a5168cfe2ecb4bb6
2024-08-10 10:17:35 +08:00
hiyouga
f0aa5b1a66 update readme
Former-commit-id: fa7bc9f1c7347153f9092ffbbb8e88c6b2f59632
2024-08-09 20:46:02 +08:00
hiyouga
45fc1dfbda add magpie ultra dataset
Former-commit-id: 3317b24329b87e30f13a78936ac5554f211abf7a
2024-08-09 20:28:55 +08:00
hiyouga
e1352c5e11 add qwen2 math models
Former-commit-id: 72ff43a1772c9de5ff914d5e1c8bdc8dea9ae0c8
2024-08-09 20:20:35 +08:00
hiyouga
956484afce update examples
Former-commit-id: d5c57c8b7f64afe8061045ec9689abbac45c1175
2024-08-09 20:13:46 +08:00
hiyouga
c7a1c3f43a add adam_mini to readme
Former-commit-id: d610c6bcf8a8ba6f4236f5d11f79571b83f4fb11
2024-08-09 20:02:03 +08:00
hoshi-hiyouga
fa486f14b0 Merge pull request #5095 from relic-yuexi/feat-optimizer
Feat optimizer

Former-commit-id: f08390d252d42a812b71a08daba7339cc40889b7
2024-08-09 19:51:33 +08:00
hiyouga
c10fd715cf update scripts
Former-commit-id: dabf5a1dc661a6581474c6a5ec115322d168ed5f
2024-08-09 19:16:23 +08:00
hiyouga
727193cdc9 follow #5115
Former-commit-id: 7d917e03e2df570139bae18227d9c7303a12de2a
2024-08-09 18:03:00 +08:00
hoshi-hiyouga
88036daf95 Merge pull request #5115 from YeQiuO/main
fix: `Train on the last turn only` truncate bug
Former-commit-id: 2c6dae45f7a7b72c961489ac407b1b444ab7752e
2024-08-09 17:58:27 +08:00
hoshi-hiyouga
d564744ab5 Merge pull request #5072 from relic-yuexi/main
fix the deepseekcoder template to avoid repeat problem

Former-commit-id: 2ae7d5c91725eab9f994015d8d3577894c7978b6
2024-08-09 16:35:21 +08:00
hoshi-hiyouga
7cbc5f3974 Update template.py
Former-commit-id: ae2a5221c109ae3474d219c37433be767abbee91
2024-08-09 16:27:42 +08:00
“Wzw”
a53c99ecda mask_history args verify valid
Former-commit-id: 2f8388b4f4195d934400ad9267d72e10ca4105a3
2024-08-08 10:12:01 +08:00
“Wzw”
cf3a209a93 fix mask_history tiny bug
Former-commit-id: cac07aac6196be026f723b2397a343d4fb675973
2024-08-08 10:09:33 +08:00
codingma
d37277dd13 fix eval_dataset in example
Former-commit-id: e1ffc54f7e58419cc8da958a4d3c2697e18d5583
2024-08-07 18:24:19 +08:00
moontidef
128cb8d2b4 feat: add support for adammini
Former-commit-id: a2d5fafb705ff44db1711e972490f0abebc2012b
2024-08-07 10:08:22 +08:00
moontidef
5243075bb7 fix: rename optimzer to optimizer
Former-commit-id: 186dc1fde822e6a603ac273538741ea3853f243e
2024-08-07 10:05:01 +08:00
moontidef
1221cf7c25 Merge branch 'hiyouga:main' into main
Former-commit-id: d1b23283e0e4286f126d38d7bdc55802f74c8922
2024-08-06 00:18:45 +08:00
moontidef
d368f7b95d fix: fix the deepseekcoder template to avoid repeat problem
Former-commit-id: 56294831115f095135f72490a8a435434b2f0a11
2024-08-05 23:55:45 +08:00
hiyouga
019a932b2f fix #5048
Former-commit-id: 71a6861667ae68c1fd6a69acf68e1359b858cf1b
2024-08-05 23:48:19 +08:00
hoshi-hiyouga
5b6430e7ac Merge pull request #5037 from codemayq/feature-gemma-2-2b
support gemma-2-2b

Former-commit-id: 6af51fadff92cd3e665c556ac073a1876f792ada
2024-08-05 23:27:37 +08:00
codingma
af9eda3e4d support gemma-2-2b
Former-commit-id: 7037192cf6049fd7d675aed4a6237ed929c6b170
2024-08-01 13:45:48 +08:00
hoshi-hiyouga
2315cf2ddb Merge pull request #5010 from Eruly/main
Add Korean web UI (llamafactory-cli webui)

Former-commit-id: 2050806aa826028df45c0c746b4314afe178dcd3
2024-07-30 01:55:54 +08:00
hoshi-hiyouga
41576eefb9 Merge pull request #4996 from LDLINGLINGLING/main
增加了MiniCPM在页面首页的支持列表,MiniCPM官方github也放了LLama_factory的友情链接

Former-commit-id: a86a776fb0f75697b0fee7694a5a0d6bd04fee0a
2024-07-30 01:55:30 +08:00
hoshi-hiyouga
15f6b33078 Update README_zh.md
Former-commit-id: 922906faf2d432def7cfdac82f90472fa1bb24a9
2024-07-30 01:55:13 +08:00
hoshi-hiyouga
c3e6ccf61e Update README.md
Former-commit-id: 6bc7f71940be0a8f1614f9036b9c539ce46d34e1
2024-07-30 01:53:19 +08:00
hoshi-hiyouga
0e404d1d3c Update README.md
Former-commit-id: 54eecdec0da06677ea55847c74642d0fc12d8908
2024-07-30 01:52:35 +08:00
hoshi-hiyouga
6f16633595 Merge pull request #4995 from codemayq/fix-pissa
fix pissa callback

Former-commit-id: 052c0f6bd9e872ea325b5a6aef98c4c070733384
2024-07-30 01:47:25 +08:00
eruly
2d650ee0d7 Add Korean web UI (llamafactory-cli webui)
Former-commit-id: 357a035f2aeb9548368c230c5a17dcdfa4844b17
2024-07-29 13:47:13 +00:00
liudan
6c2f58bc80 增加了MiniCPM在页面首页的支持列表,MiniCPM官方github也放了LLama_factory的友情链接
Former-commit-id: f482a6e2fd30aff5113e53f3f07b4649982bcc2e
2024-07-29 10:58:28 +08:00
codingma
602c21d0bd fix pissa save
Former-commit-id: 25a1dad7c8df79c15efecb8c6f871a13a327f57a
2024-07-29 10:44:34 +08:00
hiyouga
1779abec22 tiny fix
Former-commit-id: 183d8bd500a8e9513a077161ba8e8d61bea9200f
2024-07-26 11:51:00 +08:00
hoshi-hiyouga
fc3443858d Merge pull request #4892 from piamo/main
update deepseek template

Former-commit-id: 3233efc8404972098665286d9dec7312dd6ecfab
2024-07-26 11:49:34 +08:00
hoshi-hiyouga
cc3bd57a74 Merge pull request #4950 from liuwwang/main and fi
fix: Repair the issue where quantization failed after merging the adapter.
Former-commit-id: 93a68ea1f4372973f745a2c250250ecaac515e27
2024-07-26 11:48:56 +08:00
hoshi-hiyouga
6f0edb2c89 Merge pull request #4970 from HardAndHeavy/add-rocm
Add ROCm support

Former-commit-id: c0f21d869bce6e59825d57c66bce3fe54f50065f
2024-07-26 11:41:23 +08:00
hoshi-hiyouga
12af55c81f Update README_zh.md
Former-commit-id: 86a27a97ff67b0d4bcd671c62759cd049542dc1b
2024-07-26 11:30:57 +08:00
hoshi-hiyouga
f848b1463f Update README.md
Former-commit-id: 1c167bb2ea3a47bdeeccc044a653662132c61698
2024-07-26 11:29:28 +08:00
hoshi-hiyouga
84c1204c60 Update README.md
Former-commit-id: d6e7a69c274c3756587e18a039637dd37fa152b2
2024-07-26 11:29:09 +08:00