mport AutoProcessor, FlaxCLIPModel

    >>> model = FlaxCLIPModel.from_pretrained("openai/clip-vit-base-patch32")
    >>> processor = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")

    >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
    >>> image = Image.open(requests.get(url, stream=True).raw)

    >>> inputs = processor(
    ...     text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="np", padding=True
    ... )

    >>> outputs = model(**inputs)
    >>> logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
    >>> probs = jax.nn.softmax(logits_per_image, axis=1)  # we can take the softmax to get the label probabilities
    ```
)MÚ