Qwen2.5-3B-Instruct Medical + Math LoRA
Built with Qwen
LoRA adapter for Qwen2.5-3B-Instruct fine-tuned 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: LoRA (Low-Rank Adaptation)
- Framework: PEFT 0.18.1
Repository
License
Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved.
