README.md

---
library_name: transformers
license: llama3.2
base_model: chrisgru/llama-3.2-3B-r-test
tags:
- axolotl
- generated_from_trainer
- mlx
model-index:
- name: llama-3.2-3B-r-test
  results: []
---

# chrisgru/llama-3.2-3B-r-test-mlx

The Model [chrisgru/llama-3.2-3B-r-test-mlx](https://huggingface.co/chrisgru/llama-3.2-3B-r-test-mlx) was converted to MLX format from [chrisgru/llama-3.2-3B-r-test](https://huggingface.co/chrisgru/llama-3.2-3B-r-test) using mlx-lm version **0.19.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("chrisgru/llama-3.2-3B-r-test-mlx")

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)
```