From 02649b30e5c61e034d793248108af66ab33bd7de Mon Sep 17 00:00:00 2001 From: Awni Hannun Date: Tue, 3 Dec 2024 19:20:02 -0800 Subject: [PATCH] move --- llms/README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/llms/README.md b/llms/README.md index 94493701..cd0c9723 100644 --- a/llms/README.md +++ b/llms/README.md @@ -77,9 +77,7 @@ to see how to use the API in more detail. The `mlx-lm` package also comes with functionality to quantize and optionally upload models to the Hugging Face Hub. -You can convert models in the [Hugging Face -Space](https://huggingface.co/spaces/mlx-community/mlx-my-repo) or using the -Python API: +You can convert models using the Python API: ```python from mlx_lm import convert @@ -165,6 +163,10 @@ mlx_lm.convert \ --upload-repo mlx-community/my-4bit-mistral ``` +Models can also be converted and quantized directly in the +[mlx-my-repo]]https://huggingface.co/spaces/mlx-community/mlx-my-repo) Hugging +Face Space. + ### Long Prompts and Generations `mlx-lm` has some tools to scale efficiently to long prompts and generations: