support DPO training (2305.18290)

Former-commit-id: 6d98de148e4af63a7028dfaeb6cf86eb56a4488f
This commit is contained in:
hiyouga
2023-08-11 03:02:53 +08:00
parent 72dfd74005
commit ca719a8697
33 changed files with 513 additions and 192 deletions

View File

@@ -1 +0,0 @@
f967a4f6d04a11308a15524aa9a846a19a8d1e83

View File

@@ -1 +0,0 @@
0a4f0d74fd1c5cab2eb6d84a3a3fe669847becd8