README.md

---
base_model: netease-youdao/Confucius3-Math
language:
- en
library_name: transformers
license: mit
pipeline_tag: text-generation
tags:
- chat
- llama-cpp
---

# Confucius3-Math-GGUF
This model was converted to GGUF format from [`netease-youdao/Confucius3-Math`](https://huggingface.co/netease-youdao/Confucius3-Math) using llama.cpp.
Refer to the [original model card](https://huggingface.co/netease-youdao/Confucius3-Math) for more details on the model.

We provide multiple versions of GGUF, which are stored in the corresponding subdirectories respectively. However, it should be noted that we have only evaluated the quality of the BF16 precision.

## Use with llama.cpp
Before running the model, please compile and install [llama.cpp](https://github.com/ggerganov/llama.cpp) first.

### Merge the model files
Since the models we uploaded have been sliced, you need to execute the following commands to merge the models before running them.
```bash
./build/bin/llama-gguf-split --merge netease-youdao/Confucius3-Math-GGUF/confucius3-math-bf16-00001-of-00008.gguf confucius3-math-bf16.gguf
```

### Run conversation
```bash
./build/bin/llama-cli -m confucius3-math-bf16.gguf
```

## Citation
If you find our work helpful, feel free to give us a cite.
```
@misc{confucius3-math,
   author = {NetEase Youdao Team},
   title = {Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning},
   url = {https://arxiv.org/abs/2506.18330},
   month = {June},
   year = {2025}
 }