| language: | |
| - ja | |
| - en | |
| license: llama3 | |
| tags: | |
| - mlx | |
| datasets: | |
| - mc4 | |
| - wikipedia | |
| - EleutherAI/pile | |
| - oscar-corpus/colossal-oscar-1.0 | |
| - cc100 | |
| thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png | |
| inference: false | |
| # mlx-community/llama-3-youko-8b-8bit | |
| This model was converted to MLX format from [`rinna/llama-3-youko-8b`]() using mlx-lm version **0.12.1**. | |
| Refer to the [original model card](https://huggingface.co/rinna/llama-3-youko-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("mlx-community/llama-3-youko-8b-8bit") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |