PatronusAI/Llama-3-Patronus-Lynx-70B-Instruct

PatronusAI/Llama-3-Patronus-Lynx-70B-Instruct is a 70 billion parameter Llama-3-Instruct fine-tuned model developed by Patronus AI. This model is specifically designed and optimized for evaluating hallucination in RAG (Retrieval Augmented Generation) settings. It excels at determining the faithfulness of an answer to a given document, outperforming several larger commercial models in hallucination detection benchmarks.