---
base_model: yamatazen/EtherealAurora-12B-v2
library_name: transformers
tags:
- mergekit
- merge
- chatml
- mlx
- mlx-my-repo
language:
- en
- ja
license: apache-2.0
---

# Wwayu/EtherealAurora-12B-v2-mlx-4Bit

The Model [Wwayu/EtherealAurora-12B-v2-mlx-4Bit](https://huggingface.co/Wwayu/EtherealAurora-12B-v2-mlx-4Bit) was converted to MLX format from [yamatazen/EtherealAurora-12B-v2](https://huggingface.co/yamatazen/EtherealAurora-12B-v2) using mlx-lm version **0.26.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Wwayu/EtherealAurora-12B-v2-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)
```