annaovesnaatatt

better-rm-gpt2-ppo

annaovesnaatatt/better-rm-gpt2-ppo

better-rm-gpt2-ppo is a feature extraction model from annaovesnaatatt. Use it when you need embeddings to search or compare text. It is set up for transformers.

Bigger RLHF model with the reward model from annaovesnaatatt/reward-model. The reward model was trained on 3000 examples from the Anthropic/hh-rlhf dataset.