jasonXT's picture
Update README.md
46c81e8 verified
---
base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- sft
license: apache-2.0
language:
- zh
---
# 小伙伴们,该模型基于deepseek-ai/DeepSeek-R1-Distill-Qwen-7B模型和michaelwzhu/ShenNong_TCM_Dataset数据集微调而来,微调结果对比如下
- **微调前**
![image/png](https://cdn-uploads.huggingface.co/production/uploads/677231e18e0ed7713b254274/Qir9ntxwygp5QF_1QadZY.png)
- **微调后**
![image/png](https://cdn-uploads.huggingface.co/production/uploads/677231e18e0ed7713b254274/XDVHVbCnx90j1Et2SugmP.png)
# Uploaded model
- **Developed by:** jasonXT
- **License:** apache-2.0
- **Finetuned from model :** unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)