How to use smdesai/SmolVLM2-2.2B-Instruct-4bit with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("smdesai/SmolVLM2-2.2B-Instruct-4bit") model = AutoModelForMultimodalLM.from_pretrained("smdesai/SmolVLM2-2.2B-Instruct-4bit")
How to use smdesai/SmolVLM2-2.2B-Instruct-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir SmolVLM2-2.2B-Instruct-4bit smdesai/SmolVLM2-2.2B-Instruct-4bit
