|
Download CONVERT_TO_MLX.md from QuantLLM/Phi-3.5-mini-instruct-MLX: direct link, hf CLI and curl.
- Browser
- Download file 235 Bytes
-
https://huggingface.co/QuantLLM/Phi-3.5-mini-instruct-MLX/resolve/main/CONVERT_TO_MLX.md
- Command line
-
hf download hf://QuantLLM/Phi-3.5-mini-instruct-MLX/CONVERT_TO_MLX.md
-
curl -L -o CONVERT_TO_MLX.md https://huggingface.co/QuantLLM/Phi-3.5-mini-instruct-MLX/resolve/main/CONVERT_TO_MLX.md
235 Bytes
| # Convert to MLX | |
| This model was saved in HuggingFace format. | |
| To convert to MLX format on Apple Silicon: | |
| ```bash | |
| pip install mlx-lm | |
| python -m mlx_lm.convert --hf-path ./hub_staging/Phi-3.5-mini-instruct-MLX --mlx-path ./mlx_model | |
| ``` | |