HuatuoGPT-sft-data-v1

Welcome to the repository of HuatuoGPT, a large language model (LLM) trained on a massive Chinese medical corpus. Our goal with HuatuoGPT is to build a more professional "ChatGPT" for medical consultation scenarios.
Below is a list of published content:
HuatuoGPT-SFT-data: Hybrid SFT data, taking advantage of both, giving the model doctor- and patient-friendly features.
HuatuoGPT model: HuatuoGPT model weights (HuatuoGPT-7B and HuatuoGPT-13B) and online demonstration. HuatuoGPT-7B is trained on Baichuan-7B, and HuatuoGPT-13B is trained on Ziya-LLaMA-13B-Pretrain-v1.
Medical Assessment Benchmarks: Assessment Methods for Evaluating LLM in Medical Scenarios.

欢迎来到华佗GPT（HuatuoGPT）的开源仓库，该模型是基于大规模中文医学语料训练得到的大语言模型（Large Language Model，LLM）。华佗GPT的研发目标，是打造面向医疗咨询场景的专业化类ChatGPT工具。

以下为已公开的项目内容清单：
华佗GPT监督微调数据集（HuatuoGPT-SFT-data）：采用混合式监督微调数据，兼具双重优势，可为模型赋予适配医患双方的交互特性。
华佗GPT模型（HuatuoGPT model）：包含模型权重文件（HuatuoGPT-7B与HuatuoGPT-13B）以及在线演示工具。其中HuatuoGPT-7B基于Baichuan-7B基座训练得到，HuatuoGPT-13B则基于Ziya-LLaMA-13B-Pretrain-v1基座完成训练。
医学评估基准集（Medical Assessment Benchmarks）：用于评估医疗场景下大语言模型的方法体系。