stanfordnlp/pyreft Issues
[P1] About DPO training
Closed 3[P0] Adding DPO Support
Closed 9[P1] Saving/loading issues
Updated[P1] Loading REFT fro RoBERTa Models
Updated 4[P1] Contact information
Closed 1[P1] Possible to do batch inference?
Updated 3[P1] Model Compatibility
Closed 2[P1] catastrophic forgetting
Closed 1