| language: | |
| - ja | |
| - en | |
| license: llama3.1 | |
| tags: | |
| - japanese | |
| - llama | |
| - llama-3 | |
| - mlx | |
| pipeline_tag: text-generation | |
| inference: false | |
| # mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit | |
| The Model [mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit](https://huggingface.co./mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit) was converted to MLX format from [cyberagent/Llama-3.1-70B-Japanese-Instruct-2407](https://huggingface.co./cyberagent/Llama-3.1-70B-Japanese-Instruct-2407) using mlx-lm version **0.16.1**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |