R1-Qwen-7B-LORA / README.md
nbeerbower's picture
Upload folder using huggingface_hub
d8a9e4c verified
|
raw
history blame
855 Bytes
---
base_model:
- Qwen/Qwen2.5-Math-7B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
library_name: transformers
tags:
- mergekit
- peft
---
# R1-Qwen-7B-LORA
This is a LoRA extracted from a language model. It was extracted using [mergekit](https://github.com/arcee-ai/mergekit).
## LoRA Details
This LoRA adapter was extracted from [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) and uses [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) as a base.
### Parameters
The following command was used to extract this LoRA adapter:
```sh
git clone https://github.com/arcee-ai/mergekit.git
cd mergekit
git checkout 9017715655bfc346db0fd1f156f3799084b95b9e
pip install -e .
mergekit-extract-lora deepseek-ai/DeepSeek-R1-Distill-Qwen-7B Qwen/Qwen2.5-Math-7B OUTPUT_PATH --rank=64
```