| license: llama2 | |
| library_name: transformers | |
| tags: | |
| - mlx | |
| datasets: | |
| - aqua_rat | |
| - microsoft/orca-math-word-problems-200k | |
| - m-a-p/CodeFeedback-Filtered-Instruction | |
| # voxmenthe/Smaug-Llama-3-70B-Instruct-mlx-8bit | |
| The Model [voxmenthe/Smaug-Llama-3-70B-Instruct-mlx-8bit](https://huggingface.co/voxmenthe/Smaug-Llama-3-70B-Instruct-mlx-8bit) was converted to MLX format from [abacusai/Smaug-Llama-3-70B-Instruct](https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct) using mlx-lm version **0.13.1**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("voxmenthe/Smaug-Llama-3-70B-Instruct-mlx-8bit") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |