from transformers import AutoModelForImageTextToText, AutoProcessor model_id = "roskosmos19/Orca-4B-flash"processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForImageTextToText.from_pretrained(model_id, dtype="auto", device_map="auto") messages = [ {"role": "user", "content": [ {"type": "text", "text": "Ticket: 'App crashes on login since update 2.3.' " "Choice: bug | feature_request | question. Answer with the label and a confidence 0-1."} ]}]inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", enable_thinking=False, # fast System One mode / schneller System-One-Modus).to(model.device) out = model.generate(**inputs, max_new_tokens=128)print(processor.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))