Text Generation
Transformers
PyTorch
English
llama
causal-lm
Inference Endpoints
text-generation-inference

[Request] Release of Reward Model

#7
by pchiang - opened

Would the team consider releasing the reward model in addition to the trained model? Reward model could be very useful for evaluating the performance of generation, and could also make it easier for others to reproduce RLHF training.

Sign up or log in to comment