README.md

---
language:
- code
pipeline_tag: text-generation
tags:
- llama-2
- mlx
- mlx-my-repo
license: llama2
base_model: codellama/CodeLlama-13b-hf
---

# ton-An/CodeLlama-13b-hf-mlx-4Bit

The Model [ton-An/CodeLlama-13b-hf-mlx-4Bit](https://huggingface.co/ton-An/CodeLlama-13b-hf-mlx-4Bit) was converted to MLX format from [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) using mlx-lm version **0.22.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("ton-An/CodeLlama-13b-hf-mlx-4Bit")

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)
```