How to use TitanML/tinyllava-1.1b-v0.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="TitanML/tinyllava-1.1b-v0.1")
# Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("TitanML/tinyllava-1.1b-v0.1") model = AutoModelForCausalLM.from_pretrained("TitanML/tinyllava-1.1b-v0.1", device_map="auto")
SFconvertbot