README.md

---
library_name: transformers
tags:
- mergekit
- merge
- lorablated
- mlx
- mlx-my-repo
language:
- en
- ja
base_model: yamatazen/LorablatedStock-12B
---

# hobaratio/LorablatedStock-12B-mlx-4Bit

The Model [hobaratio/LorablatedStock-12B-mlx-4Bit](https://huggingface.co/hobaratio/LorablatedStock-12B-mlx-4Bit) was converted to MLX format from [yamatazen/LorablatedStock-12B](https://huggingface.co/yamatazen/LorablatedStock-12B) 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("hobaratio/LorablatedStock-12B-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)
```