johannhartmann's picture
Upload folder using huggingface_hub
ddb79af verified
|
raw
history blame
549 Bytes
---
language:
- de
license: llama3
library_name: transformers
tags:
- mlx
---
# mayflowergmbh/Llama3-German-8B-4bit
This model was converted to MLX format from [`DiscoResearch/Llama3-German-8B`]().
Refer to the [original model card](https://huggingface.co/DiscoResearch/Llama3-German-8B) for more details on the model.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mayflowergmbh/Llama3-German-8B-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```