In which licensing category does the blip_vqa license fall?

[Researcher-DL]

Hi,

I am interested in running the VQA on a series of images using the model model_type="vqav2" as loaded in the following code snippet.

from lavis.models import load_model_and_preprocess
model, vis_processors, txt_processors = load_model_and_preprocess(name="blip_vqa", model_type="vqav2", is_eval=True, device=device)
# ask a random question.
question = "Which city is this photo taken?"
image = vis_processors["eval"](raw_image).unsqueeze(0).to(device)
question = txt_processors["eval"](question)
model.predict_answers(samples={"image": image, "text_input": question}, inference_method="generate")

Could you please let me know under which licensing terms the "VQAv2" model operates? I know that the pnp-vqa model follows the BSD-3 license; does this apply to the "VQAv2" model as well?

Any information on this would be greatly appreciated. Thank you.