README.md

---
base_model: mistralai/Mamba-Codestral-7B-v0.1
license: apache-2.0
tags:
- mlx
extra_gated_description: If you want to learn more about how we process your personal
  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
---

# mlx-community/Mamba-Codestral-7B-v0.1-4bit

The Model [mlx-community/Mamba-Codestral-7B-v0.1-4bit](https://huggingface.co/mlx-community/Mamba-Codestral-7B-v0.1-4bit) was converted to MLX format from [mistralai/Mamba-Codestral-7B-v0.1](https://huggingface.co/mistralai/Mamba-Codestral-7B-v0.1) using mlx-lm version **0.18.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Mamba-Codestral-7B-v0.1-4bit")

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)
```