---
license: apache-2.0
base_model: qihoo360/Light-IF-32B
pipeline_tag: text-generation
library_name: mlx
tags:
- mlx
---

# Light-IF-32B-128k-q6-hi-mlx

This model [Light-IF-32B-128k-q6-hi-mlx](https://huggingface.co/Light-IF-32B-128k-q6-hi-mlx) was
converted to MLX format from [qihoo360/Light-IF-32B](https://huggingface.co/qihoo360/Light-IF-32B)
using mlx-lm version **0.26.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Light-IF-32B-128k-q6-hi-mlx")

prompt = "hello"

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

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