README.md

---
language:
- en
metrics:
- accuracy
base_model: Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404
pipeline_tag: text-generation
tags:
- mlx
library_name: mlx
---

# mlx-community/ReZero-v0.1-llama-3.2-3b-it-grpo-250404-8bit

This model [mlx-community/ReZero-v0.1-llama-3.2-3b-it-grpo-250404-8bit](https://huggingface.co/mlx-community/ReZero-v0.1-llama-3.2-3b-it-grpo-250404-8bit) was
converted to MLX format from [Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404](https://huggingface.co/Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404)
using mlx-lm version **0.22.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/ReZero-v0.1-llama-3.2-3b-it-grpo-250404-8bit")

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)
```