cnfusion's picture
Update README.md
c54c7b4 verified
---
license: other
license_name: msrla
license_link: LICENSE
tags:
- mlx
base_model: NyxKrage/Microsoft_Phi-4
pipeline_tag: text-generation
---
# cnfusion/Microsoft_Phi-4-Q3-mlx
The Model [cnfusion/Microsoft_Phi-4-Q3-mlx](https://huggingface.co/cnfusion/Microsoft_Phi-4-Q3-mlx) was converted to MLX format from [NyxKrage/Microsoft_Phi-4](https://huggingface.co/NyxKrage/Microsoft_Phi-4) 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("cnfusion/Microsoft_Phi-4-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)
```