本项目利用医学领域的 CoT 数据对 Deepseek-R1-Distill-Qwen-7B 进行微调,通过 QLoRA 量化和 Unsloth 加速训练,显著提升模型在复杂医学推理任务中的慢思考能力。知识蒸馏技术使轻量级模型获得大模型的推理优势,实现高效、准确且具有解释性的医学问答系统。
-
Updated
Mar 10, 2025 - Python
本项目利用医学领域的 CoT 数据对 Deepseek-R1-Distill-Qwen-7B 进行微调,通过 QLoRA 量化和 Unsloth 加速训练,显著提升模型在复杂医学推理任务中的慢思考能力。知识蒸馏技术使轻量级模型获得大模型的推理优势,实现高效、准确且具有解释性的医学问答系统。
QLoRA-enhanced Qwen2.5-3B model with 4-bit quantization for AI research Q&A.
Fine-Tuning Mistral-7B with Unsloth is a streamlined implementation for efficiently adapting the powerful Mistral-7B language model using the Unsloth framework. This project showcases low-rank adaptation (LoRA), 4-bit quantization, and structured conversational datasets to fine-tune large models with minimal memory overhead and maximum performance.
Add a description, image, and links to the 4-bit-quantization topic page so that developers can more easily learn about it.
To associate your repository with the 4-bit-quantization topic, visit your repo's landing page and select "manage topics."