README.md

---
datasets:
- togethercomputer/RedPajama-Data-V2
language:
- de
pipeline_tag: text-generation
library_name: transformers
license: other
base_model: LSX-UniWue/LLaMmlein_1B
tags:
- mlx
---

# bekrus/LLaMmlein_1B-Q8-mlx

The Model [bekrus/LLaMmlein_1B-Q8-mlx](https://huggingface.co/bekrus/LLaMmlein_1B-Q8-mlx) was converted to MLX format from [LSX-UniWue/LLaMmlein_1B](https://huggingface.co/LSX-UniWue/LLaMmlein_1B) using mlx-lm version **0.20.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("bekrus/LLaMmlein_1B-Q8-mlx")

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)
```