README.md

---
license: cc-by-nc-4.0
language:
- pl
tags:
- mlx
base_model: CYFRAGOVPL/PLLuM-12B-nc-instruct
---

# lknik/PLLuM-12B-nc-instruct-8bit

The Model [lknik/PLLuM-12B-nc-instruct-8bit](https://huggingface.co./lknik/PLLuM-12B-nc-instruct-8bit) was converted to MLX format from [CYFRAGOVPL/PLLuM-12B-nc-instruct](https://huggingface.co./CYFRAGOVPL/PLLuM-12B-nc-instruct) using mlx-lm version **0.21.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("lknik/PLLuM-12B-nc-instruct-8bit")

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)
```