Instructions to use mlx-community/SmolVLM2-500M-Video-Instruct-mlx-8bit-skip-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlx-community/SmolVLM2-500M-Video-Instruct-mlx-8bit-skip-vision with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("mlx-community/SmolVLM2-500M-Video-Instruct-mlx-8bit-skip-vision") model = AutoModelForMultimodalLM.from_pretrained("mlx-community/SmolVLM2-500M-Video-Instruct-mlx-8bit-skip-vision", device_map="auto") - MLX
How to use mlx-community/SmolVLM2-500M-Video-Instruct-mlx-8bit-skip-vision with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir SmolVLM2-500M-Video-Instruct-mlx-8bit-skip-vision mlx-community/SmolVLM2-500M-Video-Instruct-mlx-8bit-skip-vision
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "image_seq_len": 64, | |
| "processor_class": "SmolVLMProcessor" | |
| } | |