PEFT
Safetensors
qwen2
alignment-handbook
trl
dpo
Generated from Trainer
File size: 134 Bytes
76e1c78
c1e68fc
76e1c78
1
2
3
4
version https://git-lfs.github.com/spec/v1
oid sha256:867afdd56bc43fad8e12ada56d39968e0aa964f283da3d18c2df4e4d2601c257
size 323014168