Update README.md

README.md

@@ -155,10 +155,10 @@ model.eval()
 video_path = "XXXX"
 max_frames_num = 64
 video,frame_time,video_time = load_video(video_path, max_frames_num, 1, force_sample=True)
-video = image_processor.preprocess(video, return_tensors="pt")["pixel_values"].cuda().half()
+video = image_processor.preprocess(video, return_tensors="pt")["pixel_values"].cuda().to(torch.bfloat16)
 video = [video]
 conv_template = "qwen_1_5"  # Make sure you use correct chat template for different models
-time_instruciton = f"The video lasts for {video_time:.2f} seconds, and {len(video[0])} frames are uniformly sampled from it. "
+time_instruction = f"The video lasts for {video_time:.2f} seconds, and {len(video[0])} frames are uniformly sampled from it. "
 perspective_prompt = "You are seeing this video from egocentric view and you are the person. Your hands are sometimes interacting with objects. What action are you doing?"
 task_prompt = "Describe in details what you see from the video frames."
 question = DEFAULT_IMAGE_TOKEN + f"\n{time_instruction}\n{perspective_prompt} {task_prompt}"