Med42-v2：一套臨床LLM軟體套件

Med42-v2: A Suite of Clinical LLMs

August 12, 2024

作者: Clément Christophe, Praveen K Kanithi, Tathagata Raha, Shadab Khan, Marco AF Pimentel

cs.AI

摘要

Med42-v2推出了一系列臨床大型語言模型（LLMs），旨在解決醫療環境中通用模型的局限性。這些模型建立在Llama3架構上，並使用專門的臨床數據進行了微調。它們經歷了多階段的偏好對齊，以有效地回應自然提示。儘管通用模型通常會進行偏好對齊，以避免回答臨床查詢作為預防措施，但Med42-v2經過特別訓練以克服此限制，使其能夠應用於臨床環境中。Med42-v2模型在8B和70B參數配置以及各種醫學基準測試中，相對於原始Llama3模型和GPT-4，展現出卓越的性能。這些LLMs旨在理解臨床查詢，執行推理任務，並在臨床環境中提供有價值的幫助。這些模型現在可以在https://huggingface.co/m42-health{https://huggingface.co/m42-health}上公開獲取。

English

Med42-v2 introduces a suite of clinical large language models (LLMs) designed to address the limitations of generic models in healthcare settings. These models are built on Llama3 architecture and fine-tuned using specialized clinical data. They underwent multi-stage preference alignment to effectively respond to natural prompts. While generic models are often preference-aligned to avoid answering clinical queries as a precaution, Med42-v2 is specifically trained to overcome this limitation, enabling its use in clinical settings. Med42-v2 models demonstrate superior performance compared to the original Llama3 models in both 8B and 70B parameter configurations and GPT-4 across various medical benchmarks. These LLMs are developed to understand clinical queries, perform reasoning tasks, and provide valuable assistance in clinical environments. The models are now publicly available at https://huggingface.co/m42-health{https://huggingface.co/m42-health}.