Files
qwen2.5-0.5b-dpo-ultrafeedback/training_curves.png

4 lines
131 B
Plaintext
Raw Normal View History

version https://git-lfs.github.com/spec/v1
oid sha256:342416e901d5f408d9063a9320a0c302d39ad47e34a5f00099b85e77eeeceb5f
size 153238