README.md

---
pipeline_tag: text-generation
inference: true
license: apache-2.0
datasets:
- simplescaling/s1K
base_model: simplescaling/s1-32B
tags:
- mlx
---

# moot20/s1-32B-MLX-8bits

The Model [moot20/s1-32B-MLX-8bits](https://huggingface.co/moot20/s1-32B-MLX-8bits) was
converted to MLX format from [simplescaling/s1-32B](https://huggingface.co/simplescaling/s1-32B)
using mlx-lm version **0.21.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("moot20/s1-32B-MLX-8bits")

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)
```