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", device_map="auto")
https://huggingface.co/byminji/LLaVA-NeXT-13B-Video-FT/resolve/main/tokenizer.json
hf download hf://byminji/LLaVA-NeXT-13B-Video-FT/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/byminji/LLaVA-NeXT-13B-Video-FT/resolve/main/tokenizer.json
