Update README.md

README.md

@@ -196,6 +196,7 @@ 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().bfloat16()
+video = [video]
 conv_template = "qwen_1_5"  # Make sure you use correct chat template for different models
 question = DEFAULT_IMAGE_TOKEN + "\nPlease describe this video in detail."
 conv = copy.deepcopy(conv_templates[conv_template])
@@ -206,7 +207,7 @@ input_ids = tokenizer_image_token(prompt_question, tokenizer, IMAGE_TOKEN_INDEX,
 cont = model.generate(
     input_ids,
     images=video,
-    modalities="video"
+    modalities= ["video"]
     do_sample=False,
     temperature=0,
     max_new_tokens=4096,