README.md

---
license: mit
language:
- en
base_model: prithivMLmods/Phi-4-Empathetic
pipeline_tag: text-generation
library_name: transformers
tags:
- text-generation-inference
- phi
- phi3
- llama
- human_like_reasoning
- mlx
- mlx-my-repo
---

# YuHaaa/Phi-4-Empathetic-mlx-8Bit

The Model [YuHaaa/Phi-4-Empathetic-mlx-8Bit](https://huggingface.co/YuHaaa/Phi-4-Empathetic-mlx-8Bit) was converted to MLX format from [prithivMLmods/Phi-4-Empathetic](https://huggingface.co/prithivMLmods/Phi-4-Empathetic) using mlx-lm version **0.22.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("YuHaaa/Phi-4-Empathetic-mlx-8Bit")

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)
```