How to use Sourabh2/vista with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="Sourabh2/vista")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Sourabh2/vista") model = AutoModelForMultimodalLM.from_pretrained("Sourabh2/vista", device_map="auto")
https://huggingface.co/Sourabh2/vista/resolve/main/processor_config.json
hf download hf://Sourabh2/vista/processor_config.json
curl -L -o processor_config.json https://huggingface.co/Sourabh2/vista/resolve/main/processor_config.json
