Qwen2.5-3B-Instruct Medical + Math Full

Built with Qwen

Full fine-tuned Qwen2.5-3B-Instruct on medical instruction datasets plus 15% MQR data from MedCalc-Bench-v1.0 to improve medical quantitative reasoning.

Model Details

  • Base model: Qwen/Qwen2.5-3B-Instruct
  • Developed by: Caleb King
  • Type: Text generation / Instruction fine-tuned language model
  • License: qwen-research
  • Language: English

Training

  • Dataset: Med-MathInstruct (MedInstruct combined from BioInstruct and AlpaCare-MedInstruct-52k, plus MQR data from MedCalc-Bench-v1.0)
  • Method: Full instruction tuning
  • Framework: PEFT 0.18.1

Repository

https://github.com/CalebKingPortfolio/MQR-LLM-Thesis

License

Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved.

Downloads last month
57
Safetensors
Model size
3B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for calebking/qwen2.5-3b-instruct-medical-math-full

Base model

Qwen/Qwen2.5-3B
Finetuned
(1408)
this model