Transformers How to use mw-huggingface/debug_pipeline with Transformers:
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM
tokenizer = AutoTokenizer.from_pretrained("mw-huggingface/debug_pipeline")
model = AutoModelForMultimodalLM.from_pretrained("mw-huggingface/debug_pipeline") 
