How to use byminji/LLaVA-NeXT-13B-Video-FT with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("byminji/LLaVA-NeXT-13B-Video-FT") model = AutoModelForSeq2SeqLM.from_pretrained("byminji/LLaVA-NeXT-13B-Video-FT")
