How to use smdesai/SmolVLM2-2.2B-Instruct-4bit with Transformers:
# pip install -U transformers accelerate # 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", device_map="auto")
How to use smdesai/SmolVLM2-2.2B-Instruct-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download smdesai/SmolVLM2-2.2B-Instruct-4bit --local-dir SmolVLM2-2.2B-Instruct-4bit
https://huggingface.co/smdesai/SmolVLM2-2.2B-Instruct-4bit/resolve/main/processor_config.json
hf download hf://smdesai/SmolVLM2-2.2B-Instruct-4bit/processor_config.json
curl -L -o processor_config.json https://huggingface.co/smdesai/SmolVLM2-2.2B-Instruct-4bit/resolve/main/processor_config.json
