482 Commits

Author SHA1 Message Date
hiyouga
c883542583 add examples
Former-commit-id: e08045a9468986edf1e84001e6043db0ee2e5265
2024-08-30 21:43:19 +08:00
hiyouga
a83756b5e9 refactor mm training
Former-commit-id: 3382317e32f88ed377d3e7759bdeaf0f2559d22a
2024-08-30 02:14:31 +08:00
hiyouga
c2df70e925 add extra requires
Former-commit-id: d14edd350ddf268cfeea0f4e9e3c43f38516b848
2024-08-27 12:52:12 +08:00
hiyouga
c765292093 support liger kernel
Former-commit-id: 72bc8f01111ad69b92a647b54b4af988515d9c34
2024-08-27 11:20:14 +08:00
hiyouga
fc1aefa4b1 update readme
Former-commit-id: 3804ddec9e4227c02f0e0d43b7dd240cf15716a8
2024-08-19 23:32:04 +08:00
codingma
753cb0f9b6 add tutorial and doc links
Former-commit-id: 625a0e32c47aeb72a6fe9c3536914996912e89d4
2024-08-13 16:13:10 +08:00
hiyouga
684d621edc update readme
Former-commit-id: c93d55bfb084fd91436b99dba5a79aa16432e136
2024-08-10 10:17:35 +08:00
hiyouga
a0f1cc7445 update readme
Former-commit-id: 576a894f7734711a5b11ae764f42fa8d00427d4a
2024-08-09 20:46:02 +08:00
hiyouga
bea270042b add magpie ultra dataset
Former-commit-id: c75b5b83c4982a6da1512ad6f9cc4d98cc761094
2024-08-09 20:28:55 +08:00
hiyouga
a8add5c04b add qwen2 math models
Former-commit-id: dc770efb14bd6e18421511912fbb959a3cf9f78d
2024-08-09 20:20:35 +08:00
hiyouga
5eacd17090 add adam_mini to readme
Former-commit-id: e2a28f51c635d64ff9de65a37087d89356bdedcc
2024-08-09 20:02:03 +08:00
hiyouga
25b9cfa163 update scripts
Former-commit-id: 86f7099fa3fadd9c5a2059361ab5a5e1dbf5b1a2
2024-08-09 19:16:23 +08:00
hiyouga
20013e130b fix #5048
Former-commit-id: b7ca6c8dc14f689d0df16684a6121cc0ec24f8ba
2024-08-05 23:48:19 +08:00
hoshi-hiyouga
b33d668e17 Update README_zh.md
Former-commit-id: 3a49c76b65e458c0dc71fbdc810f7e50fe6293c9
2024-07-30 01:55:13 +08:00
liudan
3c3a5c09dc 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: b9ed9d45cc2bb82ab042c282ddb3e5e97b554541
2024-07-29 10:58:28 +08:00
hiyouga
884b0bbb4f tiny fix
Former-commit-id: 668654b5adae3f897d5291b81410226e1304eff9
2024-07-26 11:51:00 +08:00
hoshi-hiyouga
ca3dac9fb3 Update README_zh.md
Former-commit-id: 77e7bfee7967319da6b5cc72e88d9f6cafe065b2
2024-07-26 11:30:57 +08:00
khazic
ed5c75bd64 Added the reference address for TRL PPO details.
Former-commit-id: ceba96f9ed121bb75b8e802d9b758871a94046f1
2024-07-25 09:03:21 +08:00
hiyouga
bc36e36658 fix #4959
Former-commit-id: 77cff78863918656662b41d259b68669b7cc2237
2024-07-24 23:44:00 +08:00
hoshi-hiyouga
422771589f Update README_zh.md
Former-commit-id: 71d3e60713e1e99dd82d50aba69458fafed73089
2024-07-24 21:08:42 +08:00
hiyouga
e0875f82b3 add llama3.1
Former-commit-id: 26533c0604ef765170f93986bc06f3066c5e28ee
2024-07-24 16:20:11 +08:00
hiyouga
0d438e5cf4 update readme
Former-commit-id: 87346c094631b054ca975694416df324d2031c9a
2024-07-03 19:39:05 +08:00
wangzhihong
84f8113bb1 Update README_zh.md
Former-commit-id: 6f8f53f879faf991c494ee9655a47f905fd11867
2024-07-03 14:59:09 +08:00
hiyouga
768093c789 update readme
Former-commit-id: d4e2af1fa422caeb1a2daff7cb9af17073cab13c
2024-07-01 00:22:52 +08:00
hiyouga
bbc37b2880 fix #4398 #4592
Former-commit-id: d74244d56858d837044e5c9cea57a1b3c2ca0214
2024-06-30 21:28:51 +08:00
hiyouga
c3792dae9f update readme
Former-commit-id: 0e0d69b77c36a6110f43b0c760e9b86e2f5ee267
2024-06-28 06:55:19 +08:00
hiyouga
d3b7c489f2 add Gemma2 models
Former-commit-id: 6f63050e1b61742d5f7e48bdc62c46748031d7cb
2024-06-28 01:26:50 +08:00
hiyouga
7c488cea57 tiny fix
Former-commit-id: e44a4f07f09bbee55c10ccee91dd858256c36054
2024-06-27 20:14:48 +08:00
hoshi-hiyouga
37d3adb1f8 Merge pull request #4461 from hzhaoy/feature/support-flash-attn
support flash-attn in Dockerfile

Former-commit-id: 64b131dcfa381045cba6b77ab9e0dbf6a3934e03
2024-06-27 20:05:26 +08:00
hiyouga
d2d9fa4abb support HQQ/EETQ #4113
Former-commit-id: ad144c2265cdee0d23014dbb3d017ea257cb26ed
2024-06-27 00:29:42 +08:00
hzhaoy
c662c2e56f add flash-attn installation flag in Dockerfile
Former-commit-id: e19491b0f0446f2fb2154cf14e0b2fbba5b54808
2024-06-27 00:13:30 +08:00
hiyouga
dafc9268bc fix #4419
Former-commit-id: efb81b25ecd5cb9f4cfda8f2da8b159e4ab26a90
2024-06-25 01:51:29 +08:00
hiyouga
d519c2fde5 tiny fix
Former-commit-id: 41086059b12ecb7827eb390294e315068ff9c2e6
2024-06-25 01:15:19 +08:00
hoshi-hiyouga
678884f97c Update README_zh.md
Former-commit-id: ec95f942d1f36dee9facb687ae4168e7c3c4d3f5
2024-06-25 01:06:59 +08:00
MengqingCao
3b499948a5 update docker files
1. add docker-npu (Dockerfile and docker-compose.yml)
  2. move cuda docker to docker-cuda and tiny changes to adapt to the new path


Former-commit-id: d7207e8ad10c7df6dcb1f5e59ff8eb06f9d77e67
2024-06-24 10:57:36 +00:00
hiyouga
a1df18c5df update readme
Former-commit-id: 4ea84a833399ca434f23bdc100c0851d5b53e05b
2024-06-24 18:29:04 +08:00
hiyouga
7be502c5c5 update readme
Former-commit-id: e507e60638b2e8c66f24805b3b28f6b9f98f5924
2024-06-24 18:22:12 +08:00
hiyouga
9e5988717d tiny fix
Former-commit-id: 344b9a36b2e0b60ee61fba171b35a391e3517fed
2024-06-18 23:32:18 +08:00
hoshi-hiyouga
9b30635ff0 Merge pull request #4309 from EliMCosta/patch-1
Add Magpie and Webinstruct dataset samples

Former-commit-id: 10316dd8ca812382ddbaad0b8fce67d9b000df34
2024-06-18 23:30:19 +08:00
hiyouga
e3bf22f61b add deepseek coder v2 #4346
Former-commit-id: a233fbc258d38c62d78b9d1eaf034720361795e6
2024-06-18 22:53:54 +08:00
hiyouga
9e0ec3831f update readme
Former-commit-id: fcb2e8e7b7b79915af24c4e3264b579b3649ea90
2024-06-17 18:47:24 +08:00
Eli Costa
d7459853d8 Update README_zh.md
Fix details tag in datasets menus

Former-commit-id: 3ec57ac239a4f469bbae013ec8760307fb190189
2024-06-16 11:34:31 -03:00
Eli Costa
ee30db72a3 Update README_zh.md
Add Magpie and WebInstruct to README

Former-commit-id: 82d5c5c1e8dda61523dee4be351c18731e4a5b9c
2024-06-16 11:22:06 -03:00
hiyouga
f25b8626bf support pissa
Former-commit-id: 8c1046d78ac6c8f9429b73617e35e1eccb35138f
2024-06-16 01:08:12 +08:00
hiyouga
4dcd124dbd update readme
Former-commit-id: acd84ce5350ef985e3712a40442c6f7a54d08d40
2024-06-15 05:13:16 +08:00
hiyouga
0926d81053 update examples
Former-commit-id: b6e008c152421db668c971b0828cbee6a80b16bc
2024-06-13 03:15:06 +08:00
hiyouga
e89d1b1ec3 add neo-sft dataset
Former-commit-id: c7a5620ccc72b7574255ea764693ccb866c48263
2024-06-13 01:00:56 +08:00
hiyouga
99ce085415 fix lint
Former-commit-id: 713fde4259233af645bade7790211064a07a2a6f
2024-06-13 00:48:44 +08:00
hiyouga
b2b0b96051 fix docker compose usage
Former-commit-id: 947a34f53b74e4cd2b964941cf1580bcabde2228
2024-06-13 00:07:48 +08:00
hiyouga
77e4dc255f update readme
Former-commit-id: 2ce2e5bc478f6ffcafe8e6451b1fef4e8994694c
2024-06-12 17:39:12 +08:00