README.md

---
license: apache-2.0
language:
- en
base_model: netease-youdao/Confucius-o1-14B
tags:
- chat
- mlx
- mlx-my-repo
library_name: transformers
---

# AlfRjw/Confucius-o1-14B-Q3-mlx

**UNTESTED**

The Model [AlfRjw/Confucius-o1-14B-Q3-mlx](https://huggingface.co/AlfRjw/Confucius-o1-14B-Q3-mlx) was converted to MLX format from [netease-youdao/Confucius-o1-14B](https://huggingface.co/netease-youdao/Confucius-o1-14B) using mlx-lm version **0.20.5**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("AlfRjw/Confucius-o1-14B-Q3-mlx")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```