README.md

---
license: apache-2.0
language:
- en
base_model: POLARIS-Project/Polaris-4B-Preview
tags:
- mlx
pipeline_tag: text-generation
library_name: mlx
---

# mlx-community/Polaris-4B-Preview-8bit

This model [mlx-community/Polaris-4B-Preview-8bit](https://huggingface.co/mlx-community/Polaris-4B-Preview-8bit) was
converted to MLX format from [POLARIS-Project/Polaris-4B-Preview](https://huggingface.co/POLARIS-Project/Polaris-4B-Preview)
using mlx-lm version **0.25.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Polaris-4B-Preview-8bit")

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)
```