RLHF
#5
by
sanduntg
- opened
Is this model support RLHF?
Hi, @sanduntg , sorry that I missed the question.
Sure the model can be trained with RLHF, but I guess you question is whether we have released one. We haven't trained the model with RLHF, we did one experiment with DPO here: https://huggingface.co/LLM360/AmberSafe