from transformers import AutoModelForVision2Seq, AutoProcessorfrom PIL import Image # Load modelmodel = AutoModelForVision2Seq.from_pretrained( "zenlm/zen-vl-30b-agent", device_map="auto")processor = AutoProcessor.from_pretrained("zenlm/zen-vl-30b-agent") # Process imageimage = Image.open("example.jpg")prompt = "What's in this image?" messages = [{"role": "user", "content": prompt}]text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=text, images=image, return_tensors="pt").to(model.device) # Generateoutputs = model.generate(**inputs, max_new_tokens=256)response = processor.decode(outputs[0], skip_special_tokens=True)print(response)