geProcessor.from_pretrained("MCG-NJU/videomae-base")
        >>> model = TimesformerModel.from_pretrained("facebook/timesformer-base-finetuned-k400")

        >>> # prepare video for the model
        >>> inputs = image_processor(list(video), return_tensors="pt")

        >>> # forward pass
        >>> outputs = model(**inputs)
        >>> last_hidden_states = outputs.last_hidden_state
        >>> list(last_hidden_states.shape)
        [1, 1569, 768]
        ```NŠ