Metadata-Version: 2.1
Name: mlx-vlm
Version: 0.0.1
Summary: Vision LLMs on Apple silicon with MLX and the Hugging Face Hub
Home-page: https://github.com/Blaizzy/mlx-vlm
Author: MLX Contributors
Author-email: prince.gdt@gmail.com
License: MIT
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: mlx>=0.8.0
Requires-Dist: mlx-lm>=0.4.0
Requires-Dist: numpy
Requires-Dist: transformers
Requires-Dist: torch
Requires-Dist: huggingface_hub
Requires-Dist: Pillow
Requires-Dist: requests

# MLX-VLM

MLX-VLM a package for running Vision LLMs on your Mac using MLX.


## Get started

The easiest way to get started is to install the `mlx-vlm` package:

**With `pip`**:

```sh
pip install mlx-vlm
```

**Inference**:

```sh
python -m mlx_vlm.generate --model mlx-community/llava-1.5-7b-hf-4bit --max-tokens 10 --temp 0.0
```

**Convert models**:

```sh
pip -m mlx_vlm.convert
    --hf-path  llava-hf/llava-1.5-7b-hf\
    -q \
    --upload-repo mlx-community/llava-1.5-7b-hf-4bit
```
