README.md

---
language:
- de
- bg
- cs
- da
- el
- en
- es
- et
- fi
- fr
- ga
- hr
- hu
- it
- lt
- lv
- mt
- nl
- pl
- pt
- ro
- sl
- sv
- sk
metrics:
- accuracy
- bleu
pipeline_tag: text-generation
library_name: transformers
base_model: openGPT-X/Teuken-7B-instruct-commercial-v0.4
license: apache-2.0
tags:
- mlx
---

# stelterlab/Teuken-7B-instruct-commercial-v0.4-MLX-4bit

The Model [stelterlab/Teuken-7B-instruct-commercial-v0.4-MLX-4bit](https://huggingface.co/stelterlab/Teuken-7B-instruct-commercial-v0.4-MLX-4bit) was converted to MLX format from [openGPT-X/Teuken-7B-instruct-commercial-v0.4](https://huggingface.co/openGPT-X/Teuken-7B-instruct-commercial-v0.4) using mlx-lm version **0.19.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("stelterlab/Teuken-7B-instruct-commercial-v0.4-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)
```