---
license: apache-2.0
language:
- en
base_model: digitranslab/Megamind-v3-4B-base-instruct
pipeline_tag: text-generation
library_name: mlx
tags:
- code
- mlx
---

# digitranslab/Megamind-v3-4B-base-instruct-4bit

This model [digitranslab/Megamind-v3-4B-base-instruct-4bit](https://huggingface.co/digitranslab/Megamind-v3-4B-base-instruct-4bit) was
converted to MLX format from [digitranslab/Megamind-v3-4B-base-instruct](https://huggingface.co/digitranslab/Megamind-v3-4B-base-instruct)
using mlx-lm version **0.30.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("digitranslab/Megamind-v3-4B-base-instruct-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```