README.md

---
license: apache-2.0
library_name: mlx
tags:
- language
- granite-4.0
- mlx
base_model: ibm-granite/granite-4.0-1b
pipeline_tag: text-generation
---

# ethicalabs/granite-4.0-1b

This model [ethicalabs/granite-4.0-1b](https://huggingface.co/ethicalabs/granite-4.0-1b) was
converted to MLX format from [ibm-granite/granite-4.0-1b](https://huggingface.co/ibm-granite/granite-4.0-1b)
using mlx-lm version **0.28.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("ethicalabs/granite-4.0-1b")

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)
```