Update README.md

README.md

@@ -85,7 +85,7 @@ from PaDT import PaDTForConditionalGeneration, VisonTextProcessingClass, parseVR
 
 
 TEST_IMG_PATH="./eval/imgs/000000368335.jpg"
-MODEL_PATH="PaDT-MLLM/PaDT_Pro_3B"
+MODEL_PATH="PaDT-MLLM/PaDT_OVD_3B"
 
 # load model
 model = PaDTForConditionalGeneration.from_pretrained(MODEL_PATH, torch_dtype=torch.bfloat16, device_map={"": 0})
@@ -97,7 +97,7 @@ processor = VisonTextProcessingClass(processor, model.config.vision_config.spati
 processor.prepare(model.model.embed_tokens.weight.shape[0])
 
 # question prompt
-PROMPT = "Please describe this image."
+PROMPT = """Please carefully check the image and detect the following objects: ["person", "bicycle", "car", "motorcycle", "horse"]."""
 
 # construct conversation
 message = [