# RLHF Reward Model

Prometheus 2 is a language model based on Mistral-Instruct, specifically designed for fine-grained evaluation and reinforcement learning from human feedback, serving as an alternative to GPT-4 evaluation.

A reward model trained based on the LMFlow framework. It is trained on the HH - RLHF dataset (only the useful part) with open_llama_3b as the base model and has good generalization ability.

ToxicityModel is a fine-tuned model based on RoBERTa, designed to assess the toxicity level of English sentences.