README.md

---
license: mit
license_link: https://huggingface.co/microsoft/Phi-4-reasoning-plus/resolve/main/LICENSE
language:
- en
base_model: microsoft/Phi-4-reasoning-plus
pipeline_tag: text-generation
tags:
- phi
- nlp
- math
- code
- chat
- conversational
- reasoning
- mlx
- mlx-my-repo
inference:
  parameters:
    temperature: 0
widget:
- messages:
  - role: user
    content: What is the derivative of x^2?
library_name: transformers
---

# MCES10/Phi-4-reasoning-plus-mlx-fp16

The Model [MCES10/Phi-4-reasoning-plus-mlx-fp16](https://huggingface.co/MCES10/Phi-4-reasoning-plus-mlx-fp16) was converted to MLX format from [microsoft/Phi-4-reasoning-plus](https://huggingface.co/microsoft/Phi-4-reasoning-plus) using mlx-lm version **0.22.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("MCES10/Phi-4-reasoning-plus-mlx-fp16")

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)
```