How to use uf-aice-lab/BLIP-Math with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="uf-aice-lab/BLIP-Math")
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("uf-aice-lab/BLIP-Math") model = AutoModelForMultimodalLM.from_pretrained("uf-aice-lab/BLIP-Math", device_map="auto")
https://huggingface.co/uf-aice-lab/BLIP-Math/resolve/main/tokenizer.json
hf download hf://uf-aice-lab/BLIP-Math/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/uf-aice-lab/BLIP-Math/resolve/main/tokenizer.json
