keras-hub-nightly 0.15.0.dev20240823171555__py3-none-any.whl

keras_hub/src/models/roberta/roberta_masked_lm_preprocessor.py

@@ -0,0 +1,198 @@
+# Copyright 2024 The KerasHub Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import keras
+from absl import logging
+
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.layers.preprocessing.masked_lm_mask_generator import (
+    MaskedLMMaskGenerator,
+)
+from keras_hub.src.models.roberta.roberta_preprocessor import (
+    RobertaPreprocessor,
+)
+
+
+@keras_hub_export("keras_hub.models.RobertaMaskedLMPreprocessor")
+class RobertaMaskedLMPreprocessor(RobertaPreprocessor):
+    """RoBERTa preprocessing for the masked language modeling task.
+
+    This preprocessing layer will prepare inputs for a masked language modeling
+    task. It is primarily intended for use with the
+    `keras_hub.models.RobertaMaskedLM` task model. Preprocessing will occur in
+    multiple steps.
+
+    1. Tokenize any number of input segments using the `tokenizer`.
+    2. Pack the inputs together with the appropriate `"<s>"`, `"</s>"` and
+      `"<pad>"` tokens, i.e., adding a single `"<s>"` at the start of the
+      entire sequence, `"</s></s>"` between each segment,
+      and a `"</s>"` at the end of the entire sequence.
+    3. Randomly select non-special tokens to mask, controlled by
+      `mask_selection_rate`.
+    4. Construct a `(x, y, sample_weight)` tuple suitable for training with a
+      `keras_hub.models.RobertaMaskedLM` task model.
+
+    Args:
+        tokenizer: A `keras_hub.models.RobertaTokenizer` instance.
+        sequence_length: int. The length of the packed inputs.
+        truncate: string. The algorithm to truncate a list of batched segments
+            to fit within `sequence_length`. The value can be either
+            `round_robin` or `waterfall`:
+            - `"round_robin"`: Available space is assigned one token at a
+                time in a round-robin fashion to the inputs that still need
+                some, until the limit is reached.
+            - `"waterfall"`: The allocation of the budget is done using a
+                "waterfall" algorithm that allocates quota in a
+                left-to-right manner and fills up the buckets until we run
+                out of budget. It supports an arbitrary number of segments.
+        mask_selection_rate: float. The probability an input token will be
+            dynamically masked.
+        mask_selection_length: int. The maximum number of masked tokens
+            in a given sample.
+        mask_token_rate: float. The probability the a selected token will be
+            replaced with the mask token.
+        random_token_rate: float. The probability the a selected token will be
+            replaced with a random token from the vocabulary. A selected token
+            will be left as is with probability
+            `1 - mask_token_rate - random_token_rate`.
+
+    Call arguments:
+        x: A tensor of single string sequences, or a tuple of multiple
+            tensor sequences to be packed together. Inputs may be batched or
+            unbatched. For single sequences, raw python inputs will be converted
+            to tensors. For multiple sequences, pass tensors directly.
+        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.
+
+    Examples:
+
+    Directly calling the layer on data.
+    ```python
+    # Load the preprocessor from a preset.
+    preprocessor = keras_hub.models.RobertaMaskedLMPreprocessor.from_preset(
+        "roberta_base_en"
+    )
+
+    # Tokenize and mask a single sentence.
+    preprocessor("The quick brown fox jumped.")
+
+    # Tokenize and mask a batch of single sentences.
+    preprocessor(["The quick brown fox jumped.", "Call me Ishmael."])
+
+    # Tokenize and mask sentence pairs.
+    # In this case, always convert input to tensors before calling the layer.
+    first = tf.constant(["The quick brown fox jumped.", "Call me Ishmael."])
+    second = tf.constant(["The fox tripped.", "Oh look, a whale."])
+    preprocessor((first, second))
+    ```
+
+    Mapping with `tf.data.Dataset`.
+    ```python
+    preprocessor = keras_hub.models.RobertaMaskedLMPreprocessor.from_preset(
+        "roberta_base_en"
+    )
+
+    first = tf.constant(["The quick brown fox jumped.", "Call me Ishmael."])
+    second = tf.constant(["The fox tripped.", "Oh look, a whale."])
+
+    # Map single sentences.
+    ds = tf.data.Dataset.from_tensor_slices(first)
+    ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
+
+    # Map sentence pairs.
+    ds = tf.data.Dataset.from_tensor_slices((first, second))
+    # Watch out for tf.data's default unpacking of tuples here!
+    # Best to invoke the `preprocessor` directly in this case.
+    ds = ds.map(
+        lambda first, second: preprocessor(x=(first, second)),
+        num_parallel_calls=tf.data.AUTOTUNE,
+    )
+    ```
+    """
+
+    def __init__(
+        self,
+        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,
+    ):
+        super().__init__(
+            tokenizer,
+            sequence_length=sequence_length,
+            truncate=truncate,
+            **kwargs,
+        )
+        self.mask_selection_rate = mask_selection_rate
+        self.mask_selection_length = mask_selection_length
+        self.mask_token_rate = mask_token_rate
+        self.random_token_rate = random_token_rate
+        self.masker = None
+
+    def build(self, input_shape):
+        super().build(input_shape)
+        # Defer packer creation to `build()` so that we can be sure tokenizer
+        # assets have loaded when restoring a saved model.
+        self.masker = MaskedLMMaskGenerator(
+            mask_selection_rate=self.mask_selection_rate,
+            mask_selection_length=self.mask_selection_length,
+            mask_token_rate=self.mask_token_rate,
+            random_token_rate=self.random_token_rate,
+            vocabulary_size=self.tokenizer.vocabulary_size(),
+            mask_token_id=self.tokenizer.mask_token_id,
+            unselectable_token_ids=[
+                self.tokenizer.start_token_id,
+                self.tokenizer.end_token_id,
+                self.tokenizer.pad_token_id,
+            ],
+        )
+        self.built = True
+
+    def call(self, x, y=None, sample_weight=None):
+        if y is not None or sample_weight is not None:
+            logging.warning(
+                f"{self.__class__.__name__} generates `y` and `sample_weight` "
+                "based on your input data, but your data already contains `y` "
+                "or `sample_weight`. Your `y` and `sample_weight` will be "
+                "ignored."
+            )
+
+        x = super().call(x)
+        token_ids, padding_mask = x["token_ids"], x["padding_mask"]
+        masker_outputs = self.masker(token_ids)
+        x = {
+            "token_ids": masker_outputs["token_ids"],
+            "padding_mask": padding_mask,
+            "mask_positions": masker_outputs["mask_positions"],
+        }
+        y = masker_outputs["mask_ids"]
+        sample_weight = masker_outputs["mask_weights"]
+        return keras.utils.pack_x_y_sample_weight(x, y, sample_weight)
+
+    def get_config(self):
+        config = super().get_config()
+        config.update(
+            {
+                "mask_selection_rate": self.mask_selection_rate,
+                "mask_selection_length": self.mask_selection_length,
+                "mask_token_rate": self.mask_token_rate,
+                "random_token_rate": self.random_token_rate,
+            }
+        )
+        return config

keras_hub/src/models/roberta/roberta_preprocessor.py

@@ -0,0 +1,192 @@
+# Copyright 2024 The KerasHub Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+import keras
+
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.layers.preprocessing.multi_segment_packer import (
+    MultiSegmentPacker,
+)
+from keras_hub.src.models.preprocessor import Preprocessor
+from keras_hub.src.models.roberta.roberta_tokenizer import RobertaTokenizer
+from keras_hub.src.utils.keras_utils import (
+    convert_inputs_to_list_of_tensor_segments,
+)
+
+
+@keras_hub_export("keras_hub.models.RobertaPreprocessor")
+class RobertaPreprocessor(Preprocessor):
+    """A RoBERTa preprocessing layer which tokenizes and packs inputs.
+
+    This preprocessing layer will do three things:
+
+    1. Tokenize any number of input segments using the `tokenizer`.
+    2. Pack the inputs together with the appropriate `"<s>"`, `"</s>"` and
+       `"<pad>"` tokens, i.e., adding a single `"<s>"` at the start of the
+       entire sequence, `"</s></s>"` at the end of each segment, save the last
+       and a `"</s>"` at the end of the entire sequence.
+    3. Construct a dictionary with keys `"token_ids"`, `"padding_mask"` that
+       can be passed directly to a RoBERTa model.
+
+    This layer can be used directly with `tf.data.Dataset.map` to preprocess
+    string data in the `(x, y, sample_weight)` format used by
+    `keras.Model.fit`.
+
+    Args:
+        tokenizer: A `keras_hub.models.RobertaTokenizer` instance.
+        sequence_length: The length of the packed inputs.
+        truncate: string. The algorithm to truncate a list of batched segments
+            to fit within `sequence_length`. The value can be either
+            `round_robin` or `waterfall`:
+            - `"round_robin"`: Available space is assigned one token at a
+                time in a round-robin fashion to the inputs that still need
+                some, until the limit is reached.
+            - `"waterfall"`: The allocation of the budget is done using a
+                "waterfall" algorithm that allocates quota in a
+                left-to-right manner and fills up the buckets until we run
+                out of budget. It supports an arbitrary number of segments.
+
+    Call arguments:
+        x: A tensor of single string sequences, or a tuple of multiple
+            tensor sequences to be packed together. Inputs may be batched or
+            unbatched. For single sequences, raw python inputs will be converted
+            to tensors. For multiple sequences, pass tensors directly.
+        y: Any label data. Will be passed through unaltered.
+        sample_weight: Any label weight data. Will be passed through unaltered.
+
+
+    Examples:
+
+    Directly calling the layer on data.
+    ```python
+    preprocessor = keras_hub.models.RobertaPreprocessor.from_preset(
+        "roberta_base_en"
+    )
+
+    # Tokenize and pack a single sentence.
+    preprocessor("The quick brown fox jumped.")
+
+    # Tokenize a batch of single sentences.
+    preprocessor(["The quick brown fox jumped.", "Call me Ishmael."])
+
+    # Preprocess a batch of sentence pairs.
+    # When handling multiple sequences, always convert to tensors first!
+    first = tf.constant(["The quick brown fox jumped.", "Call me Ishmael."])
+    second = tf.constant(["The fox tripped.", "Oh look, a whale."])
+    preprocessor((first, second))
+
+    # Custom vocabulary.
+    vocab = {"<s>": 0, "<pad>": 1, "</s>": 2, "<mask>": 3}
+    vocab = {**vocab, "a": 4, "Ġquick": 5, "Ġfox": 6}
+    merges = ["Ġ q", "u i", "c k", "ui ck", "Ġq uick", "Ġ f", "o x", "Ġf ox"]
+    tokenizer = keras_hub.models.RobertaTokenizer(
+        vocabulary=vocab,
+        merges=merges
+    )
+    preprocessor = keras_hub.models.RobertaPreprocessor(tokenizer)
+    preprocessor("a quick fox")
+    ```
+    Mapping with `tf.data.Dataset`.
+    ```python
+    preprocessor = keras_hub.models.RobertaPreprocessor.from_preset(
+        "roberta_base_en"
+    )
+
+    first = tf.constant(["The quick brown fox jumped.", "Call me Ishmael."])
+    second = tf.constant(["The fox tripped.", "Oh look, a whale."])
+    label = tf.constant([1, 1])
+
+    # Map labeled single sentences.
+    ds = tf.data.Dataset.from_tensor_slices((first, label))
+    ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
+
+    # Map unlabeled single sentences.
+    ds = tf.data.Dataset.from_tensor_slices(first)
+    ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
+
+    # Map labeled sentence pairs.
+    ds = tf.data.Dataset.from_tensor_slices(((first, second), label))
+    ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
+
+    # Map unlabeled sentence pairs.
+    ds = tf.data.Dataset.from_tensor_slices((first, second))
+    # Watch out for tf.data's default unpacking of tuples here!
+    # Best to invoke the `preprocessor` directly in this case.
+    ds = ds.map(
+        lambda first, second: preprocessor(x=(first, second)),
+        num_parallel_calls=tf.data.AUTOTUNE,
+    )
+    ```
+    """
+
+    tokenizer_cls = RobertaTokenizer
+
+    def __init__(
+        self,
+        tokenizer,
+        sequence_length=512,
+        truncate="round_robin",
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.tokenizer = tokenizer
+        self.packer = None
+        self.truncate = truncate
+        self.sequence_length = sequence_length
+
+    def build(self, input_shape):
+        # Defer packer creation to `build()` so that we can be sure tokenizer
+        # assets have loaded when restoring a saved model.
+        self.packer = MultiSegmentPacker(
+            start_value=self.tokenizer.start_token_id,
+            end_value=self.tokenizer.end_token_id,
+            sep_value=[self.tokenizer.end_token_id] * 2,
+            pad_value=self.tokenizer.pad_token_id,
+            truncate=self.truncate,
+            sequence_length=self.sequence_length,
+        )
+        self.built = True
+
+    def call(self, x, y=None, sample_weight=None):
+        x = convert_inputs_to_list_of_tensor_segments(x)
+        x = [self.tokenizer(segment) for segment in x]
+        token_ids, _ = self.packer(x)
+        x = {
+            "token_ids": token_ids,
+            "padding_mask": token_ids != self.tokenizer.pad_token_id,
+        }
+        return keras.utils.pack_x_y_sample_weight(x, y, sample_weight)
+
+    def get_config(self):
+        config = super().get_config()
+        config.update(
+            {
+                "sequence_length": self.sequence_length,
+                "truncate": self.truncate,
+            }
+        )
+        return config
+
+    @property
+    def sequence_length(self):
+        """The padded length of model input sequences."""
+        return self._sequence_length
+
+    @sequence_length.setter
+    def sequence_length(self, value):
+        self._sequence_length = value
+        if self.packer is not None:
+            self.packer.sequence_length = value

keras_hub/src/models/roberta/roberta_presets.py

@@ -0,0 +1,43 @@
+# Copyright 2024 The KerasHub Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""RoBERTa model preset configurations."""
+
+backbone_presets = {
+    "roberta_base_en": {
+        "metadata": {
+            "description": (
+                "12-layer RoBERTa model where case is maintained."
+                "Trained on English Wikipedia, BooksCorpus, CommonCraw, and OpenWebText."
+            ),
+            "params": 124052736,
+            "official_name": "RoBERTa",
+            "path": "roberta",
+            "model_card": "https://github.com/facebookresearch/fairseq/blob/main/examples/roberta/README.md",
+        },
+        "kaggle_handle": "kaggle://keras/roberta/keras/roberta_base_en/2",
+    },
+    "roberta_large_en": {
+        "metadata": {
+            "description": (
+                "24-layer RoBERTa model where case is maintained."
+                "Trained on English Wikipedia, BooksCorpus, CommonCraw, and OpenWebText."
+            ),
+            "params": 354307072,
+            "official_name": "RoBERTa",
+            "path": "roberta",
+            "model_card": "https://github.com/facebookresearch/fairseq/blob/main/examples/roberta/README.md",
+        },
+        "kaggle_handle": "kaggle://keras/roberta/keras/roberta_large_en/2",
+    },
+}

keras_hub/src/models/roberta/roberta_tokenizer.py

@@ -0,0 +1,132 @@
+# Copyright 2024 The KerasHub Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.tokenizers.byte_pair_tokenizer import BytePairTokenizer
+
+
+@keras_hub_export("keras_hub.models.RobertaTokenizer")
+class RobertaTokenizer(BytePairTokenizer):
+    """A RoBERTa tokenizer using Byte-Pair Encoding subword segmentation.
+
+    This tokenizer class will tokenize raw strings into integer sequences and
+    is based on `keras_hub.tokenizers.BytePairTokenizer`. Unlike the
+    underlying tokenizer, it will check for all special tokens needed by RoBERTa
+    models and provides a `from_preset()` method to automatically download
+    a matching vocabulary for a RoBERTa preset.
+
+    This tokenizer does not provide truncation or padding of inputs. It can be
+    combined with a `keras_hub.models.RobertaPreprocessor` layer for input
+    packing.
+
+    If input is a batch of strings (rank > 0), the layer will output a
+    `tf.RaggedTensor` where the last dimension of the output is ragged.
+
+    If input is a scalar string (rank == 0), the layer will output a dense
+    `tf.Tensor` with static shape `[None]`.
+
+    Args:
+        vocabulary: A dictionary mapping tokens to integer ids, or file path
+            to a json file containing the token to id mapping.
+        merges: A list of merge rules or a string file path, If passing a file
+            path. the file should have one merge rule per line. Every merge
+            rule contains merge entities separated by a space.
+
+    Examples:
+    ```python
+    # Unbatched input.
+    tokenizer = keras_hub.models.RobertaTokenizer.from_preset(
+        "roberta_base_en",
+    )
+    tokenizer("The quick brown fox jumped.")
+
+    # Batched input.
+    tokenizer(["The quick brown fox jumped.", "The fox slept."])
+
+    # Detokenization.
+    tokenizer.detokenize(tokenizer("The quick brown fox jumped."))
+
+    # Custom vocabulary.
+    # Note: 'Ġ' is space
+    vocab = {"<s>": 0, "<pad>": 1, "</s>": 2, "<mask>": 3}
+    vocab = {**vocab, "a": 4, "Ġquick": 5, "Ġfox": 6}
+    merges = ["Ġ q", "u i", "c k", "ui ck", "Ġq uick"]
+    merges += ["Ġ f", "o x", "Ġf ox"]
+    tokenizer = keras_hub.models.RobertaTokenizer(
+        vocabulary=vocab,
+        merges=merges
+    )
+    tokenizer(["a quick fox", "a fox quick"])
+    ```
+    """
+
+    def __init__(
+        self,
+        vocabulary=None,
+        merges=None,
+        **kwargs,
+    ):
+        self.start_token = "<s>"
+        self.pad_token = "<pad>"
+        self.end_token = "</s>"
+        self.mask_token = "<mask>"
+
+        super().__init__(
+            vocabulary=vocabulary,
+            merges=merges,
+            unsplittable_tokens=[
+                self.start_token,
+                self.pad_token,
+                self.end_token,
+                self.mask_token,
+            ],
+            **kwargs,
+        )
+
+    def set_vocabulary_and_merges(self, vocabulary, merges):
+        super().set_vocabulary_and_merges(vocabulary, merges)
+
+        if vocabulary is not None:
+            # Check for necessary special tokens.
+            for token in [
+                self.start_token,
+                self.pad_token,
+                self.end_token,
+                self.mask_token,
+            ]:
+                if token not in self.vocabulary:
+                    raise ValueError(
+                        f"Cannot find token `'{token}'` in the provided "
+                        f"`vocabulary`. Please provide `'{token}'` in your "
+                        "`vocabulary` or use a pretrained `vocabulary` name."
+                    )
+
+            self.start_token_id = self.token_to_id(self.start_token)
+            self.pad_token_id = self.token_to_id(self.pad_token)
+            self.end_token_id = self.token_to_id(self.end_token)
+            self.mask_token_id = self.token_to_id(self.mask_token)
+        else:
+            self.start_token_id = None
+            self.pad_token_id = None
+            self.end_token_id = None
+            self.mask_token_id = None
+
+    def get_config(self):
+        config = super().get_config()
+        # In the constructor, we pass the list of special tokens to the
+        # `unsplittable_tokens` arg of the superclass' constructor. Hence, we
+        # delete it from the config here.
+        del config["unsplittable_tokens"]
+        return config

keras_hub/src/models/seq_2_seq_lm.py

@@ -0,0 +1,54 @@
+# Copyright 2024 The KerasHub Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.models.causal_lm import CausalLM
+
+
+@keras_hub_export("keras_hub.models.Seq2SeqLM")
+class Seq2SeqLM(CausalLM):
+    """Base class for sequence to sequence language modeling tasks.
+
+    `Seq2SeqLM` tasks wrap a `keras_hub.models.Backbone` and
+    a `keras_hub.models.Preprocessor` to create a model that can be used for
+    generation and generative fine-tuning, when generation is conditioned on
+    additional input sequence in a sequence-to-sequence setting.
+
+    `Seq2SeqLM` tasks provide an additional, high-level `generate()` function
+    which can be used to auto-regressively sample an output sequence token by
+    token. The `compile()` method of `Seq2SeqLM` classes contains an additional
+    `sampler` argument, which can be used to pass a `keras_hub.samplers.Sampler`
+    to control how the predicted distribution will be sampled.
+
+    When calling `fit()`, each input should contain an input and output
+    sequence. The model will be trained to predict the output sequence
+    token-by-token using a causal mask, similar to a `keras_hub.models.CausalLM`
+    task. Unlike the `CausalLM` task, an input sequence must be passed, and
+    can be attended to in full by all tokens in the output sequence.
+
+    All `Seq2SeqLM` tasks include a `from_preset()` constructor which can be
+    used to load a pre-trained config and weights.
+
+    Example:
+    ```python
+    # Load a Bart backbone with pre-trained weights.
+    seq_2_seq_lm = keras_hub.models.Seq2SeqLM.from_preset(
+        "bart_base_en",
+    )
+    seq_2_seq_lm.compile(sampler="top_k")
+    # Generate conditioned on the `"The quick brown fox."` as an input sequence.
+    seq_2_seq_lm.generate("The quick brown fox.", max_length=30)
+    ```
+    """
+
+    # TODO: fill in during https://github.com/keras-team/keras-hub/pull/1425

keras_hub/src/models/t5/__init__.py

@@ -0,0 +1,20 @@
+# Copyright 2024 The KerasHub Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from keras_hub.src.models.t5.t5_backbone import T5Backbone
+from keras_hub.src.models.t5.t5_presets import backbone_presets
+from keras_hub.src.models.t5.t5_tokenizer import T5Tokenizer
+from keras_hub.src.utils.preset_utils import register_presets
+
+register_presets(backbone_presets, (T5Backbone, T5Tokenizer))