T5GemmaSeq2SeqLMPreprocessor layer

[source]

T5GemmaSeq2SeqLMPreprocessor class

keras_hub.models.T5GemmaSeq2SeqLMPreprocessor(
    tokenizer,
    encoder_sequence_length=512,
    decoder_sequence_length=512,
    add_start_token=False,
    add_end_token=True,
    **kwargs
)

T5Gemma Seq2Seq LM preprocessor.

This preprocessing layer is meant for use with keras_hub.models.T5GemmaSeq2SeqLM. By default, it will take in batches of strings, and return outputs in a (x, y, sample_weight) format, where the y label is the next token id in the x sequence.

For use with generation, the layer also exposes two methods generate_preprocess() and generate_postprocess(). When this preprocessor is attached to a keras_hub.models.T5GemmaSeq2SeqLM instance, these methods will be called implicitly in generate(). They can also be called standalone (e.g. to precompute preprocessing inputs for generation in a separate process).

Arguments

• tokenizer: A keras_hub.models.T5GemmaTokenizer instance.
• encoder_sequence_length: The length of the packed encoder inputs.
• decoder_sequence_length: The length of the packed decoder inputs.
• add_start_token: If True, the preprocessor will prepend the tokenizer start token to each input sequence. For T5Gemma models, this should be False. Defaults to False.
• add_end_token: If True, the preprocessor will append the tokenizer end token to each input sequence. For T5Gemma models, this should be True. Defaults to True.

Call arguments

• x: A dictionary with two keys, "encoder_text" and "decoder_text". The values can be a string, a tf.Tensor or a list of python strings.
• y: Label data. Should always be None as the layer generates labels.
• sample_weight: Label weights. Should always be None as the layer generates label weights.
• encoder_sequence_length: Pass to override the configured encoder_sequence_length of the layer.
• decoder_sequence_length: Pass to override the configured decoder_sequence_length of the layer.

Examples

import tensorflow as tf
import numpy as np

# Load the preprocessor from a preset.
preprocessor = keras_hub.models.T5GemmaSeq2SeqLMPreprocessor.from_preset(
    "t5gemma_b_b_prefixlm_it"
)

# For example usage, see the dictionary example below which provides
# both encoder and decoder text.
# Tokenize a batch of sentences.
preprocessor(["The quick brown fox jumped.", "Call me Ishmael."])
# Tokenize a dictionary with separate encoder and decoder inputs.
preprocessor({
    "encoder_text": "The quick brown fox jumped.",
    "decoder_text": "The fast fox."
})

# Apply tokenization to a [`tf.data.Dataset`](https://www.tensorflow.org/api_docs/python/tf/data/Dataset).
encoder_features = tf.constant(["The quick brown fox.", "Call me Ishmael."])
decoder_features = tf.constant(["The fast fox.", "I am Ishmael."])
ds = tf.data.Dataset.from_tensor_slices(
    {"encoder_text": encoder_features, "decoder_text": decoder_features}
)
ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)

# Prepare tokens for generation.
preprocessor.generate_preprocess({
    "encoder_text": "The quick brown fox jumped.",
    "decoder_text": "The fast fox."
})

# Map generation outputs back to strings.
preprocessor.generate_postprocess({
    'decoder_token_ids': np.array([[2, 714, 4320, 8426, 25341, 1, 0, 0]]),
    'decoder_padding_mask': np.array([[1, 1, 1, 1, 1, 1, 0, 0]]),
})

[source]

from_preset method

T5GemmaSeq2SeqLMPreprocessor.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.CausalLMPreprocessor.from_preset(
    "gemma_2b_en",
)

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

[source]

generate_preprocess method

T5GemmaSeq2SeqLMPreprocessor.generate_preprocess(
    x, encoder_sequence_length=None, decoder_sequence_length=None, sequence_length=None
)

Convert input strings to integer token inputs for generation.

Similar to calling the layer for training, this method takes in a dict containing "encoder_text" and "decoder_text", with strings or tensor strings for values, tokenizes and packs the input, and computes a padding mask masking all inputs not filled in with a padded value.

Unlike calling the layer for training, this method does not compute labels and will never append a tokenizer.end_token_id to the end of the decoder sequence (as generation is expected to continue at the end of the inputted decoder prompt).

[source]

generate_postprocess method

T5GemmaSeq2SeqLMPreprocessor.generate_postprocess(x)

Convert integer token output to strings for generation.

This method reverses generate_preprocess(), by first removing all padding and start/end tokens, and then converting the integer sequence back to a string.

tokenizer property

keras_hub.models.T5GemmaSeq2SeqLMPreprocessor.tokenizer

The tokenizer used to tokenize strings.