How to use mlx-community/SmolVLM2-256M-Video-Instruct-mlx with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("mlx-community/SmolVLM2-256M-Video-Instruct-mlx") model = AutoModelForMultimodalLM.from_pretrained("mlx-community/SmolVLM2-256M-Video-Instruct-mlx", device_map="auto")
How to use mlx-community/SmolVLM2-256M-Video-Instruct-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/SmolVLM2-256M-Video-Instruct-mlx --local-dir SmolVLM2-256M-Video-Instruct-mlx
https://huggingface.co/mlx-community/SmolVLM2-256M-Video-Instruct-mlx/resolve/refs%2Fpr%2F3/processor_config.json
hf download hf://mlx-community/SmolVLM2-256M-Video-Instruct-mlx@refs/pr/3/processor_config.json
curl -L -o processor_config.json https://huggingface.co/mlx-community/SmolVLM2-256M-Video-Instruct-mlx/resolve/refs%2Fpr%2F3/processor_config.json
