How to use Video-Reason/VBVR-Pro-BAGEL with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-image" 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-image", model="Video-Reason/VBVR-Pro-BAGEL")
# pip install -U transformers accelerate # Load model directly from transformers import Bagel model = Bagel.from_pretrained("Video-Reason/VBVR-Pro-BAGEL", device_map="auto")
https://huggingface.co/Video-Reason/VBVR-Pro-BAGEL/resolve/main/vocab.json
hf download hf://Video-Reason/VBVR-Pro-BAGEL/vocab.json
curl -L -o vocab.json https://huggingface.co/Video-Reason/VBVR-Pro-BAGEL/resolve/main/vocab.json
