import torchfrom transformers import AutoModelForImageTextToText, AutoProcessor model_id = "ScarletKc/ScarletKc-2.0"processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForImageTextToText.from_pretrained( model_id, dtype=torch.bfloat16, device_map="auto",) messages = [ {"role": "user", "content": [{"type": "text", "text": "你是谁?介绍一下你自己吧"}]}]inputs = processor.apply_chat_template( messages, add_generation_prompt=True, enable_thinking=True, reasoning_effort="xhigh", tokenize=True, return_dict=True, return_tensors="pt",).to(model.device) out = model.generate( **inputs, max_new_tokens=1024, do_sample=True, temperature=0.6, top_p=0.9, top_k=20,)print(processor.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=False))