MaskedLMPreprocessor

[source]

MaskedLMPreprocessor class

keras_nlp.models.MaskedLMPreprocessor(
    tokenizer,
    sequence_length=512,
    truncate="round_robin",
    mask_selection_rate=0.15,
    mask_selection_length=96,
    mask_token_rate=0.8,
    random_token_rate=0.1,
    **kwargs
)

Base class for masked language modeling preprocessing layers.

MaskedLMPreprocessor tasks wrap a keras_hub.tokenizer.Tokenizer to create a preprocessing layer for masked language modeling tasks. It is intended to be paired with a keras.models.MaskedLM task.

All MaskedLMPreprocessor take inputs a single input. This can be a single string, a batch of strings, or a tuple of batches of string segments that should be combined into a single sequence. See examples below. These inputs will be tokenized, combined, and masked randomly along the sequence.

This layer will always output a (x, y, sample_weight) tuple, where x is a dictionary with the masked, tokenized inputs, y contains the tokens that were masked in x, and sample_weight marks where y contains padded values. The exact contents of x will vary depending on the model being used.

All MaskedLMPreprocessor tasks include a from_preset() constructor which can be used to load a pre-trained config and vocabularies. You can call the from_preset() constructor directly on this base class, in which case the correct class for you model will be automatically instantiated.

Examples.

preprocessor = keras_hub.models.MaskedLMPreprocessor.from_preset(
    "bert_base_en_uncased",
    sequence_length=256, # Optional.
)

# Tokenize, mask and pack a single sentence.
x = "The quick brown fox jumped."
x, y, sample_weight = preprocessor(x)

# Preprocess a batch of labeled sentence pairs.
first = ["The quick brown fox jumped.", "Call me Ishmael."]
second = ["The fox tripped.", "Oh look, a whale."]
x, y, sample_weight = preprocessor((first, second))

# With a [`tf.data.Dataset`](https://www.tensorflow.org/api_docs/python/tf/data/Dataset).
ds = tf.data.Dataset.from_tensor_slices((first, second))
ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)

[source]

from_preset method

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

Instantiate a keras_hub.models.Preprocessor from a model preset.

A preset is a directory of configs, weights and other file assets used to save and load a pre-trained model. The preset can be passed as one of:

1. a built-in preset identifier like 'bert_base_en'
2. a Kaggle Models handle like 'kaggle://user/bert/keras/bert_base_en'
3. a Hugging Face handle like 'hf://user/bert_base_en'
4. a path to a local preset directory like './bert_base_en'

For any Preprocessor subclass, you can run cls.presets.keys() to list all built-in presets available on the class.

As there are usually multiple preprocessing classes for a given model, this method should be called on a specific subclass like keras_hub.models.BertTextClassifierPreprocessor.from_preset().

Arguments

• preset: string. A built-in preset identifier, a Kaggle Models handle, a Hugging Face handle, or a path to a local directory.

Examples

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

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

[source]

save_to_preset method

MaskedLMPreprocessor.save_to_preset(preset_dir)

Save preprocessor to a preset directory.

Arguments

• preset_dir: The path to the local model preset directory.

tokenizer property

keras_nlp.models.MaskedLMPreprocessor.tokenizer

The tokenizer used to tokenize strings.