HuggingFaceM4/the_cauldron
Viewer • Updated • 1.88M • 422k • 531
How to use mlx-community/SmolVLM2-256M-Video-Instruct-mlx with Transformers:
# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText
processor = AutoProcessor.from_pretrained("mlx-community/SmolVLM2-256M-Video-Instruct-mlx")
model = AutoModelForImageTextToText.from_pretrained("mlx-community/SmolVLM2-256M-Video-Instruct-mlx")How to use mlx-community/SmolVLM2-256M-Video-Instruct-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir SmolVLM2-256M-Video-Instruct-mlx mlx-community/SmolVLM2-256M-Video-Instruct-mlx
This model was converted to MLX format from HuggingFaceTB/SmolVLM2-256M-Video-Instruct using mlx-vlm version 0.1.13.
Refer to the original model card for more details on the model.
pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/SmolVLM2-256M-Video-Instruct-mlx --image https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg --prompt "Can you describe this image?"
Quantized
Base model
HuggingFaceTB/SmolLM2-360M