Qwen-SFT
Collection
A series of fine-tuned models based on the Qwen model
•
5 items
•
Updated
使用以下8个数据集
对Qwen1.5-7B-Chat进行微调并测试,结果显示,微调后的模型在CEVAL和MMLU的评分上均有所提升。
https://github.com/hiyouga/LLaMA-Factory
使用opencompass(https://github.com/open-compass/OpenCompass/ ), 测试工具基于CEval和MMLU对微调之后的模型和原始模型进行测试。
测试模型分别为:
8*A800
大约750Mb的微调数据集
模型名称 | CEVAL | MMLU |
---|---|---|
Qwen1.5-7B-Chat | 68.61 | 61.56 |
Qwen1.5-7B-Chat-750Mb-lora | 71.36 | 61.78 |
This project utilizes certain datasets and checkpoints that are subject to their respective original licenses. Users must comply with all terms and conditions of these original licenses. The content of this project itself is licensed under the Apache license 2.0.