# LLaMA Fine-tuning

The Beaver Cost Model is a preference model trained on the PKU-SafeRLHF dataset, designed to evaluate the safety of model outputs in safe RLHF algorithms.

Preference model trained on PKU-SafeRLHF dataset for optimizing Beaver models in safe RLHF algorithms

MedLLaMA_13B is a large language model for the medical domain, fine-tuned on partial medical corpora based on the LLaMA-13b architecture.