MonteXiaofeng/CareBot_Medical_multi-llama3-8b-instruct

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:Sep 29, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

MonteXiaofeng/CareBot_Medical_multi-llama3-8b-instruct is an 8 billion parameter instruction-tuned causal language model, based on the Llama 3 architecture, developed by MonteXiaofeng. It is specifically fine-tuned for medical instruction following and healthcare scenarios, leveraging a diverse dataset of medical dialogues and consultations. This model excels at tasks like disease diagnosis, health consultations, and answering medical exam questions, making it suitable for medical AI applications.

Loading preview...

CareBot_Medical_multi-llama3-8b-instruct Overview

This model, developed by MonteXiaofeng, is an 8 billion parameter Llama 3-based instruction-tuned language model specifically designed for medical applications. It is fine-tuned from the MonteXiaofeng/CareBot_Medical_multi-llama3-8b-base model to enhance its ability to follow medical instructions and adapt to specific healthcare scenarios.

Key Capabilities & Training

The model's supervised fine-tuning (SFT) process utilizes conversational-style data, including queries and responses, to improve its performance in medical contexts. The SFT dataset is constructed from a diverse array of question types, integrating data from seven publicly available sources such as Chinese Medical Dialogue Data, Huatuo26M, MedDialog, ChatMed Consult Dataset, ChatDoctor, CMB, and MedQA. This dataset includes:

  • Multiple-choice questions from medical exams.
  • Single-turn disease diagnoses.
  • Multi-turn health consultations.

To ensure diversity, the dataset incorporates authentic doctor-patient conversations and augments content by rewriting real-world medical scenarios using GPT-4 generated responses. This comprehensive training aims to enable CareBot to adapt to various medical problems and patient situations.

Evaluation

The model's performance has been evaluated on benchmarks, with results presented in the original README, including comparisons with other medical LLMs, indicating its specialized capabilities in the medical domain.