update processor kwargs

README.md

@@ -104,7 +104,7 @@ prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
 
 image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"
 raw_image = Image.open(requests.get(image_file, stream=True).raw)
-inputs = processor(prompt, raw_image, return_tensors='pt').to(0, torch.float16)
+inputs = processor(images=raw_image, text=prompt, return_tensors='pt').to(0, torch.float16)
 
 output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
 print(processor.decode(output[0][2:], skip_special_tokens=True))
@@ -119,7 +119,7 @@ When prompting with videos/3D/multi-view input, prompt like following:
 image_tokens = "<image>" * n
 prompt = f"<|im_start|>user {image_tokens}\nWhat are these?|im_end|><|im_start|>assistant"
 
-# With chat template if you sampled 6 frames you have to have 8 images in one conversation turn
+# With chat template if you sampled 5 frames you have to have 5 images in one conversation turn
 conversation = [
     {