README.md

---
base_model: ifable/gemma-2-Ifable-9B
datasets:
- jondurbin/gutenberg-dpo-v0.1
library_name: transformers
license: gemma
tags:
- mlx
---

# cyan2k/gemma-2-Ifable-9B-mlx-4bit

The Model [cyan2k/gemma-2-Ifable-9B-mlx-4bit](https://huggingface.co/cyan2k/gemma-2-Ifable-9B-mlx-4bit) was converted to MLX format from [ifable/gemma-2-Ifable-9B](https://huggingface.co/ifable/gemma-2-Ifable-9B) 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("cyan2k/gemma-2-Ifable-9B-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)
```