Gemma3CausalLMPreprocessor layer

keras_hub.models.Gemma3CausalLMPreprocessor(
    tokenizer,
    image_converter=None,
    sequence_length=1024,
    add_start_token=True,
    add_end_token=True,
    max_images_per_prompt=2,
    num_vision_tokens_per_image=256,
    **kwargs
)

# === Language Gemma3 model ===
# Load the preprocessor from a preset.
preprocessor = keras_hub.models.Gemma3CausalLMPreprocessor.from_preset(
    "gemma3_instruct_1b"
)

# Unbatched inputs.
preprocessor(
    {
        "prompts": "What is the capital of India?",
        "responses": "New Delhi",
    }
)

# Batched inputs.
preprocessor(
    {
        "prompts": [
            "What is the capital of India?",
            "What is the capital of Spain?"
        ],
        "responses": ["New Delhi", "Madrid"],
    }
)

# Apply preprocessing to a [`tf.data.Dataset`](https://www.tensorflow.org/api_docs/python/tf/data/Dataset).
features = {
    "prompts": [
        "What is the capital of India?",
        "What is the capital of Spain?"
    ],
    "responses": ["New Delhi", "Madrid"],
}

ds = tf.data.Dataset.from_tensor_slices(features)
ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)

# Prepare tokens for generation (no end token).
preprocessor.generate_preprocess(["The quick brown fox jumped."])

# Map generation outputs back to strings.
preprocessor.generate_postprocess({
    'token_ids': np.array([[2, 818, 3823, 8864, 37423, 32694, 236761, 0]]),
    'padding_mask': np.array([[ 1, 1, 1, 1, 1, 1, 1, 0]]),
})

# === Vision and Language Gemma3 model ===
# Load the preprocessor from a preset.
preprocessor = keras_hub.models.Gemma3CausalLMPreprocessor.from_preset(
    "gemma3_instruct_4b"
)

# text-only inputs (unbatched)
preprocessor(
    {
        "prompts": "What is the capital of India?",
        "responses": "New Delhi",
    }
)

# text-only inputs (batched)
preprocessor(
    {
        "prompts": [
            "What is the capital of India?",
            "What is the capital of Spain?"
        ],
        "responses": ["New Delhi", "Madrid"],
    }
)

# Unbatched inputs, with one image.
preprocessor(
    {
        "prompts": "this is a lily <start_of_image>",
        "responses": "pristine!",
        "images": np.ones((896, 896, 3), dtype="float32")
    }
)

# Unbatched inputs, with two images.
preprocessor(
    {
        "prompts": "lily: <start_of_image>, sunflower: <start_of_image>",
        "responses": "pristine!",
        "images": [
            np.ones((896, 896, 3), dtype="float32"),
            np.ones((896, 896, 3), dtype="float32")
        ],
    }
)

# Batched inputs, one image per prompt.
preprocessor(
    {
        "prompts": [
            "this is a lily: <start_of_image>",
            "this is a sunflower: <start_of_image>"
        ],
        "responses": ["pristine!", "radiant!"],
        "images": [
            np.ones((896, 896, 3), dtype="float32"),
            np.ones((896, 896, 3), dtype="float32")
        ]
    }
)

# Can also be written this way.
preprocessor(
    {
        "prompts": [
            "this is a lily: <start_of_image>",
            "this is a sunflower: <start_of_image>"
        ],
        "responses": ["pristine!", "radiant!"],
        "images": [
            [np.ones((896, 896, 3), dtype="float32")],
            [np.ones((896, 896, 3), dtype="float32")]
        ]
    }
)

# Different number of images in every sample.
preprocessor(
    {
        "prompts": [
            "Who is this singer: <start_of_image>?",
            "Who are these musicians <start_of_image>, <start_of_image>?"
        ],
        "responses": ["Arijit Singh", "John Lennon, Paul Mccartney"],
        "images": [
            [
                np.ones((896, 896, 3), dtype="float32"),
                np.ones((896, 896, 3), dtype="float32")
            ],
            [np.ones((896, 896, 3), dtype="float32")]
        ]
    }
)

# Apply preprocessing to a [`tf.data.Dataset`](https://www.tensorflow.org/api_docs/python/tf/data/Dataset).
inputs = {
    "prompts": [
        "Who are these two: <start_of_image>, <start_of_image>",
        "Who is this: <start_of_image>?",
        "What is the capital of India?"
    ],
    "responses": [
        "John Lennon, Paul Mccartney",
        "Arijit Singh",
        "New Delhi"
    ],
    "images": (
        tf.ragged.constant(
            [
                [np.ones((10, 10, 3)), np.ones((10, 10, 3))],
                [np.ones((10, 10, 3))],
                [],
            ]
        )
    )
}
ds = tf.data.Dataset.from_tensor_slices(inputs)
ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)

Gemma3CausalLMPreprocessor.from_preset(
    preset, config_file="preprocessor.json", **kwargs
)

# Load a preprocessor for Gemma generation.
preprocessor = keras_hub.models.CausalLMPreprocessor.from_preset(
    "gemma_2b_en",
)

# Load a preprocessor for Bert classification.
preprocessor = keras_hub.models.TextClassifierPreprocessor.from_preset(
    "bert_base_en",
)

keras_hub.models.Gemma3CausalLMPreprocessor.tokenizer