from PIL import Imagefrom peft import PeftModelfrom transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration base_model_id = "Qwen/Qwen2.5-VL-3B-Instruct"adapter_repo_or_path = "qualcomm-ai-hub-community/OpenSparX-3b-cabin-lora-v2" processor = AutoProcessor.from_pretrained(base_model_id, trust_remote_code=True)base_model = Qwen2_5_VLForConditionalGeneration.from_pretrained( base_model_id, torch_dtype="auto", device_map="auto", trust_remote_code=True,)model = PeftModel.from_pretrained(base_model, adapter_repo_or_path) image = Image.open("/path/to/your/image.jpg").convert("RGB")messages = [ { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": "Describe the driver state and suggest actions."}, ], }] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt")inputs = inputs.to(base_model.device) generated_ids = model.generate(**inputs, max_new_tokens=128)generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, generated_ids)]print(processor.batch_decode(generated_ids, skip_special_tokens=False)[0])