keras-hub-nightly 0.16.1.dev202410200345__tar.gz → 0.19.0.dev202412070351__tar.gz

{keras_hub_nightly-0.16.1.dev202410200345 → keras_hub_nightly-0.19.0.dev202412070351}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: keras-hub-nightly
-Version: 0.16.1.dev202410200345
+Version: 0.19.0.dev202412070351
 Summary: Industry-strength Natural Language Processing extensions for Keras.
 Home-page: https://github.com/keras-team/keras-hub
 Author: Keras team
@@ -37,11 +37,8 @@ Requires-Dist: sentencepiece; extra == "extras"
 [![contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://github.com/keras-team/keras-hub/issues)
 
 > [!IMPORTANT]
-> 📢 KerasNLP is becoming KerasHub! 📢 Read
+> 📢 KerasNLP is now KerasHub! 📢 Read
 > [the announcement](https://github.com/keras-team/keras-hub/issues/1831).
->
-> We have renamed the repo to KerasHub in preparation for the release, but have not yet
-> released the new package. Follow the announcement for news.
 
 KerasHub is a library that supports natural language processing, computer
 vision, audio, and multimodal backbones and task models, working natively with
@@ -59,7 +56,7 @@ All models support JAX, TensorFlow, and PyTorch from a single model
 definition and can be fine-tuned on GPUs and TPUs out of the box. Models can
 be trained on individual accelerators with built-in PEFT techniques, or
 fine-tuned at scale with model and data parallel training. See our
-[Getting Started guide](https://keras.io/guides/keras_nlp/getting_started)
+[Getting Started guide](https://keras.io/guides/keras_hub/getting_started)
 to start learning our API. Browse our models on
 [Kaggle](https://www.kaggle.com/organizations/keras/models).
 We welcome contributions.
@@ -68,9 +65,9 @@ We welcome contributions.
 
 ### For everyone
 
-- [Home Page](https://keras.io/keras_nlp)
-- [Developer Guides](https://keras.io/guides/keras_nlp)
-- [API Reference](https://keras.io/api/keras_nlp)
+- [Home Page](https://keras.io/keras_hub)
+- [Developer Guides](https://keras.io/guides/keras_hub)
+- [API Reference](https://keras.io/api/keras_hub)
 - [Pre-trained Models](https://www.kaggle.com/organizations/keras/models)
 
 ### For contributors
@@ -89,7 +86,7 @@ Fine-tune a BERT classifier on IMDb movie reviews:
 import os
 os.environ["KERAS_BACKEND"] = "jax"  # Or "tensorflow" or "torch"!
 
-import keras_nlp
+import keras_hub
 import tensorflow_datasets as tfds
 
 imdb_train, imdb_test = tfds.load(
@@ -100,7 +97,7 @@ imdb_train, imdb_test = tfds.load(
 )
 
 # Load a BERT model.
-classifier = keras_nlp.models.Classifier.from_preset(
+classifier = keras_hub.models.Classifier.from_preset(
     "bert_base_en",
     num_classes=2,
     activation="softmax",
@@ -112,25 +109,17 @@ classifier.fit(imdb_train, validation_data=imdb_test)
 classifier.predict(["What an amazing movie!", "A total waste of my time."])
 ```
 
-Try it out [in a colab](https://colab.research.google.com/gist/mattdangerw/e457e42d5ea827110c8d5cb4eb9d9a07/kerasnlp-quickstart.ipynb).
+Try it out [in a colab](https://colab.research.google.com/drive/1gSWkh3yOLwmKAaNh2dQQ6kQIlnGte7P2?usp=sharing).
 For more in depth guides and examples, visit
-[keras.io/keras_nlp](https://keras.io/keras_nlp/).
+[keras.io/keras_hub](https://keras.io/keras_hub/).
 
 ## Installation
 
-KerasHub is currently in pre-release. Note that pre-release versions may
-introduce breaking changes to the API in future versions. For a stable and
-supported experience, we recommend installing `keras-nlp` version 0.15.1:
-
-```bash
-pip install keras-nlp==0.15.1
-```
-
-To try out the latest pre-release version of KerasHub, you can use
+To try out the latest version of KerasHub, you can use
 our nightly package:
 
 ```bash
-pip install keras-hub-nightly
+pip install keras-hub
 ```
 
 KerasHub currently requires TensorFlow to be installed for use of the

{keras_hub_nightly-0.16.1.dev202410200345 → keras_hub_nightly-0.19.0.dev202412070351}/README.md

@@ -4,11 +4,8 @@
 [![contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://github.com/keras-team/keras-hub/issues)
 
 > [!IMPORTANT]
-> 📢 KerasNLP is becoming KerasHub! 📢 Read
+> 📢 KerasNLP is now KerasHub! 📢 Read
 > [the announcement](https://github.com/keras-team/keras-hub/issues/1831).
->
-> We have renamed the repo to KerasHub in preparation for the release, but have not yet
-> released the new package. Follow the announcement for news.
 
 KerasHub is a library that supports natural language processing, computer
 vision, audio, and multimodal backbones and task models, working natively with
@@ -26,7 +23,7 @@ All models support JAX, TensorFlow, and PyTorch from a single model
 definition and can be fine-tuned on GPUs and TPUs out of the box. Models can
 be trained on individual accelerators with built-in PEFT techniques, or
 fine-tuned at scale with model and data parallel training. See our
-[Getting Started guide](https://keras.io/guides/keras_nlp/getting_started)
+[Getting Started guide](https://keras.io/guides/keras_hub/getting_started)
 to start learning our API. Browse our models on
 [Kaggle](https://www.kaggle.com/organizations/keras/models).
 We welcome contributions.
@@ -35,9 +32,9 @@ We welcome contributions.
 
 ### For everyone
 
-- [Home Page](https://keras.io/keras_nlp)
-- [Developer Guides](https://keras.io/guides/keras_nlp)
-- [API Reference](https://keras.io/api/keras_nlp)
+- [Home Page](https://keras.io/keras_hub)
+- [Developer Guides](https://keras.io/guides/keras_hub)
+- [API Reference](https://keras.io/api/keras_hub)
 - [Pre-trained Models](https://www.kaggle.com/organizations/keras/models)
 
 ### For contributors
@@ -56,7 +53,7 @@ Fine-tune a BERT classifier on IMDb movie reviews:
 import os
 os.environ["KERAS_BACKEND"] = "jax"  # Or "tensorflow" or "torch"!
 
-import keras_nlp
+import keras_hub
 import tensorflow_datasets as tfds
 
 imdb_train, imdb_test = tfds.load(
@@ -67,7 +64,7 @@ imdb_train, imdb_test = tfds.load(
 )
 
 # Load a BERT model.
-classifier = keras_nlp.models.Classifier.from_preset(
+classifier = keras_hub.models.Classifier.from_preset(
     "bert_base_en",
     num_classes=2,
     activation="softmax",
@@ -79,25 +76,17 @@ classifier.fit(imdb_train, validation_data=imdb_test)
 classifier.predict(["What an amazing movie!", "A total waste of my time."])
 ```
 
-Try it out [in a colab](https://colab.research.google.com/gist/mattdangerw/e457e42d5ea827110c8d5cb4eb9d9a07/kerasnlp-quickstart.ipynb).
+Try it out [in a colab](https://colab.research.google.com/drive/1gSWkh3yOLwmKAaNh2dQQ6kQIlnGte7P2?usp=sharing).
 For more in depth guides and examples, visit
-[keras.io/keras_nlp](https://keras.io/keras_nlp/).
+[keras.io/keras_hub](https://keras.io/keras_hub/).
 
 ## Installation
 
-KerasHub is currently in pre-release. Note that pre-release versions may
-introduce breaking changes to the API in future versions. For a stable and
-supported experience, we recommend installing `keras-nlp` version 0.15.1:
-
-```bash
-pip install keras-nlp==0.15.1
-```
-
-To try out the latest pre-release version of KerasHub, you can use
+To try out the latest version of KerasHub, you can use
 our nightly package:
 
 ```bash
-pip install keras-hub-nightly
+pip install keras-hub
 ```
 
 KerasHub currently requires TensorFlow to be installed for use of the

{keras_hub_nightly-0.16.1.dev202410200345 → keras_hub_nightly-0.19.0.dev202412070351}/keras_hub/api/layers/__init__.py

@@ -14,6 +14,7 @@ from keras_hub.src.layers.modeling.position_embedding import PositionEmbedding
 from keras_hub.src.layers.modeling.reversible_embedding import (
     ReversibleEmbedding,
 )
+from keras_hub.src.layers.modeling.rms_normalization import RMSNormalization
 from keras_hub.src.layers.modeling.rotary_embedding import RotaryEmbedding
 from keras_hub.src.layers.modeling.sine_position_encoding import (
     SinePositionEncoding,
@@ -34,12 +35,16 @@ from keras_hub.src.layers.preprocessing.multi_segment_packer import (
 from keras_hub.src.layers.preprocessing.random_deletion import RandomDeletion
 from keras_hub.src.layers.preprocessing.random_swap import RandomSwap
 from keras_hub.src.layers.preprocessing.start_end_packer import StartEndPacker
+from keras_hub.src.models.clip.clip_image_converter import CLIPImageConverter
 from keras_hub.src.models.deeplab_v3.deeplab_v3_image_converter import (
     DeepLabV3ImageConverter,
 )
 from keras_hub.src.models.densenet.densenet_image_converter import (
     DenseNetImageConverter,
 )
+from keras_hub.src.models.efficientnet.efficientnet_image_converter import (
+    EfficientNetImageConverter,
+)
 from keras_hub.src.models.mit.mit_image_converter import MiTImageConverter
 from keras_hub.src.models.pali_gemma.pali_gemma_image_converter import (
     PaliGemmaImageConverter,
@@ -47,9 +52,16 @@ from keras_hub.src.models.pali_gemma.pali_gemma_image_converter import (
 from keras_hub.src.models.resnet.resnet_image_converter import (
     ResNetImageConverter,
 )
+from keras_hub.src.models.retinanet.anchor_generator import AnchorGenerator
+from keras_hub.src.models.retinanet.retinanet_image_converter import (
+    RetinaNetImageConverter,
+)
 from keras_hub.src.models.sam.sam_image_converter import SAMImageConverter
 from keras_hub.src.models.sam.sam_mask_decoder import SAMMaskDecoder
 from keras_hub.src.models.sam.sam_prompt_encoder import SAMPromptEncoder
+from keras_hub.src.models.segformer.segformer_image_converter import (
+    SegFormerImageConverter,
+)
 from keras_hub.src.models.vgg.vgg_image_converter import VGGImageConverter
 from keras_hub.src.models.whisper.whisper_audio_converter import (
     WhisperAudioConverter,

{keras_hub_nightly-0.16.1.dev202410200345 → keras_hub_nightly-0.19.0.dev202412070351}/keras_hub/api/models/__init__.py

@@ -53,8 +53,11 @@ from keras_hub.src.models.bloom.bloom_causal_lm_preprocessor import (
 from keras_hub.src.models.bloom.bloom_tokenizer import BloomTokenizer
 from keras_hub.src.models.causal_lm import CausalLM
 from keras_hub.src.models.causal_lm_preprocessor import CausalLMPreprocessor
+from keras_hub.src.models.clip.clip_backbone import CLIPBackbone
 from keras_hub.src.models.clip.clip_preprocessor import CLIPPreprocessor
+from keras_hub.src.models.clip.clip_text_encoder import CLIPTextEncoder
 from keras_hub.src.models.clip.clip_tokenizer import CLIPTokenizer
+from keras_hub.src.models.clip.clip_vision_encoder import CLIPVisionEncoder
 from keras_hub.src.models.csp_darknet.csp_darknet_backbone import (
     CSPDarkNetBackbone,
 )
@@ -128,6 +131,12 @@ from keras_hub.src.models.distil_bert.distil_bert_tokenizer import (
 from keras_hub.src.models.efficientnet.efficientnet_backbone import (
     EfficientNetBackbone,
 )
+from keras_hub.src.models.efficientnet.efficientnet_image_classifier import (
+    EfficientNetImageClassifier,
+)
+from keras_hub.src.models.efficientnet.efficientnet_image_classifier_preprocessor import (
+    EfficientNetImageClassifierPreprocessor,
+)
 from keras_hub.src.models.electra.electra_backbone import ElectraBackbone
 from keras_hub.src.models.electra.electra_tokenizer import ElectraTokenizer
 from keras_hub.src.models.f_net.f_net_backbone import FNetBackbone
@@ -153,6 +162,11 @@ from keras_hub.src.models.falcon.falcon_causal_lm_preprocessor import (
 )
 from keras_hub.src.models.falcon.falcon_tokenizer import FalconTokenizer
 from keras_hub.src.models.feature_pyramid_backbone import FeaturePyramidBackbone
+from keras_hub.src.models.flux.flux_model import FluxBackbone
+from keras_hub.src.models.flux.flux_text_to_image import FluxTextToImage
+from keras_hub.src.models.flux.flux_text_to_image_preprocessor import (
+    FluxTextToImagePreprocessor,
+)
 from keras_hub.src.models.gemma.gemma_backbone import GemmaBackbone
 from keras_hub.src.models.gemma.gemma_causal_lm import GemmaCausalLM
 from keras_hub.src.models.gemma.gemma_causal_lm_preprocessor import (
@@ -176,6 +190,10 @@ from keras_hub.src.models.image_classifier import ImageClassifier
 from keras_hub.src.models.image_classifier_preprocessor import (
     ImageClassifierPreprocessor,
 )
+from keras_hub.src.models.image_object_detector import ImageObjectDetector
+from keras_hub.src.models.image_object_detector_preprocessor import (
+    ImageObjectDetectorPreprocessor,
+)
 from keras_hub.src.models.image_segmenter import ImageSegmenter
 from keras_hub.src.models.image_segmenter_preprocessor import (
     ImageSegmenterPreprocessor,
@@ -243,6 +261,13 @@ from keras_hub.src.models.resnet.resnet_image_classifier import (
 from keras_hub.src.models.resnet.resnet_image_classifier_preprocessor import (
     ResNetImageClassifierPreprocessor,
 )
+from keras_hub.src.models.retinanet.retinanet_backbone import RetinaNetBackbone
+from keras_hub.src.models.retinanet.retinanet_object_detector import (
+    RetinaNetObjectDetector,
+)
+from keras_hub.src.models.retinanet.retinanet_object_detector_preprocessor import (
+    RetinaNetObjectDetectorPreprocessor,
+)
 from keras_hub.src.models.roberta.roberta_backbone import RobertaBackbone
 from keras_hub.src.models.roberta.roberta_masked_lm import RobertaMaskedLM
 from keras_hub.src.models.roberta.roberta_masked_lm_preprocessor import (
@@ -266,6 +291,13 @@ from keras_hub.src.models.sam.sam_image_segmenter import SAMImageSegmenter
 from keras_hub.src.models.sam.sam_image_segmenter_preprocessor import (
     SAMImageSegmenterPreprocessor,
 )
+from keras_hub.src.models.segformer.segformer_backbone import SegFormerBackbone
+from keras_hub.src.models.segformer.segformer_image_segmenter import (
+    SegFormerImageSegmenter,
+)
+from keras_hub.src.models.segformer.segformer_image_segmenter_preprocessor import (
+    SegFormerImageSegmenterPreprocessor,
+)
 from keras_hub.src.models.seq_2_seq_lm import Seq2SeqLM
 from keras_hub.src.models.seq_2_seq_lm_preprocessor import Seq2SeqLMPreprocessor
 from keras_hub.src.models.stable_diffusion_3.stable_diffusion_3_backbone import (

keras_hub_nightly-0.19.0.dev202412070351/keras_hub/src/bounding_box/__init__.py

@@ -0,0 +1,2 @@
+# TODO: Once all bounding boxes are moved to keras repostory remove the
+# bounding box folder.

{keras_hub_nightly-0.16.1.dev202410200345 → keras_hub_nightly-0.19.0.dev202412070351}/keras_hub/src/bounding_box/converters.py

@@ -20,29 +20,74 @@ class RequiresImagesException(Exception):
 ALL_AXES = 4
 
 
-def _encode_box_to_deltas(
+def encode_box_to_deltas(
     anchors,
     boxes,
-    anchor_format: str,
-    box_format: str,
+    anchor_format,
+    box_format,
+    encoding_format="center_yxhw",
     variance=None,
     image_shape=None,
 ):
-    """Converts bounding_boxes from `center_yxhw` to delta format."""
+    """Encodes bounding boxes relative to anchors as deltas.
+
+    This function calculates the deltas that represent the difference between
+    bounding boxes and provided anchors. Deltas encode the offsets and scaling
+    factors to apply to anchors to obtain the target boxes.
+
+    Boxes and anchors are first converted to the specified `encoding_format`
+    (defaulting to `center_yxhw`) for consistent delta representation.
+
+    Args:
+        anchors: `Tensors`. Anchor boxes with shape of `(N, 4)` where N is the
+            number of anchors.
+        boxes:  `Tensors` Bounding boxes to encode. Boxes can be of shape
+            `(B, N, 4)` or `(N, 4)`.
+        anchor_format: str. The format of the input `anchors`
+            (e.g., "xyxy", "xywh", etc.).
+        box_format: str. The format of the input `boxes`
+            (e.g., "xyxy", "xywh", etc.).
+        encoding_format: str. The intermediate format to which boxes and anchors
+            are converted before delta calculation. Defaults to "center_yxhw".
+        variance: `List[float]`. A 4-element array/tensor representing variance
+            factors to scale the box deltas. If provided, the calculated deltas
+            are divided by the variance. Defaults to None.
+        image_shape: `Tuple[int]`. The shape of the image (height, width, 3).
+            When using relative bounding box format for `box_format` the
+            `image_shape` is used for normalization.
+    Returns:
+        Encoded box deltas. The return type matches the `encode_format`.
+
+    Raises:
+        ValueError: If `variance` is not None and its length is not 4.
+        ValueError: If `encoding_format` is not `"center_xywh"` or
+            `"center_yxhw"`.
+
+    """
     if variance is not None:
         variance = ops.convert_to_tensor(variance, "float32")
         var_len = variance.shape[-1]
 
         if var_len != 4:
             raise ValueError(f"`variance` must be length 4, got {variance}")
+
+    if encoding_format not in ["center_xywh", "center_yxhw"]:
+        raise ValueError(
+            "`encoding_format` should be one of 'center_xywh' or 'center_yxhw', "
+            f"got {encoding_format}"
+        )
+
     encoded_anchors = convert_format(
         anchors,
         source=anchor_format,
-        target="center_yxhw",
+        target=encoding_format,
         image_shape=image_shape,
     )
     boxes = convert_format(
-        boxes, source=box_format, target="center_yxhw", image_shape=image_shape
+        boxes,
+        source=box_format,
+        target=encoding_format,
+        image_shape=image_shape,
     )
     anchor_dimensions = ops.maximum(
         encoded_anchors[..., 2:], keras.backend.epsilon()
@@ -61,15 +106,54 @@ def _encode_box_to_deltas(
     return boxes_delta
 
 
-def _decode_deltas_to_boxes(
+def decode_deltas_to_boxes(
     anchors,
     boxes_delta,
-    anchor_format: str,
-    box_format: str,
+    anchor_format,
+    box_format,
+    encoded_format="center_yxhw",
     variance=None,
     image_shape=None,
 ):
-    """Converts bounding_boxes from delta format to `center_yxhw`."""
+    """Converts bounding boxes from delta format to the specified `box_format`.
+
+    This function decodes bounding box deltas relative to anchors to obtain the
+    final bounding box coordinates. The boxes are encoded in a specific
+    `encoded_format` (center_yxhw by default) during the decoding process.
+    This allows flexibility in how the deltas are applied to the anchors.
+
+    Args:
+        anchors: Can be `Tensors` or `Dict[Tensors]` where keys are level
+            indices and values are corresponding anchor boxes.
+            The shape of the array/tensor should be `(N, 4)` where N is the
+            number of anchors.
+        boxes_delta Can be `Tensors` or `Dict[Tensors]` Bounding box deltas
+            must have the same type and structure as `anchors`.  The
+            shape of the array/tensor can be `(N, 4)` or `(B, N, 4)` where N is
+            the number of boxes.
+        anchor_format: str. The format of the input `anchors`.
+            (e.g., `"xyxy"`, `"xywh"`, etc.)
+        box_format: str. The desired format for the output boxes.
+            (e.g., `"xyxy"`, `"xywh"`, etc.)
+        encoded_format: str. Raw output format from regression head. Defaults
+            to `"center_yxhw"`.
+        variance: `List[floats]`. A 4-element array/tensor representing
+            variance factors to scale the box deltas. If provided, the deltas
+            are multiplied by the variance before being applied to the anchors.
+            Defaults to None.
+        image_shape:  The shape of the image (height, width).  This is needed
+            if normalization to image size is required when converting between
+            formats. Defaults to None.
+
+    Returns:
+        Decoded box coordinates. The return type matches the `box_format`.
+
+    Raises:
+        ValueError: If `variance` is not None and its length is not 4.
+        ValueError: If `encoded_format` is not `"center_xywh"` or
+            `"center_yxhw"`.
+
+    """
     if variance is not None:
         variance = ops.convert_to_tensor(variance, "float32")
         var_len = variance.shape[-1]
@@ -77,11 +161,17 @@ def _decode_deltas_to_boxes(
         if var_len != 4:
             raise ValueError(f"`variance` must be length 4, got {variance}")
 
+    if encoded_format not in ["center_xywh", "center_yxhw"]:
+        raise ValueError(
+            f"`encoded_format` should be 'center_xywh' or 'center_yxhw', "
+            f"but got '{encoded_format}'."
+        )
+
     def decode_single_level(anchor, box_delta):
         encoded_anchor = convert_format(
             anchor,
             source=anchor_format,
-            target="center_yxhw",
+            target=encoded_format,
             image_shape=image_shape,
         )
         if variance is not None:
@@ -97,7 +187,7 @@ def _decode_deltas_to_boxes(
         )
         box = convert_format(
             box,
-            source="center_yxhw",
+            source=encoded_format,
             target=box_format,
             image_shape=image_shape,
         )

keras_hub_nightly-0.19.0.dev202412070351/keras_hub/src/layers/modeling/rms_normalization.py

@@ -0,0 +1,34 @@
+import keras
+from keras import ops
+
+from keras_hub.src.api_export import keras_hub_export
+
+
+@keras_hub_export("keras_hub.layers.RMSNormalization")
+class RMSNormalization(keras.layers.Layer):
+    """
+    Root Mean Square (RMS) Normalization layer.
+    This layer normalizes the input tensor based on its RMS value and applies
+    a learned scaling factor.
+    Args:
+        input_dim: int. The dimensionality of the input tensor.
+    """
+
+    def __init__(self, input_dim):
+        super().__init__()
+        self.scale = self.add_weight(
+            name="scale", shape=(input_dim,), initializer="ones"
+        )
+
+    def call(self, x):
+        """
+        Applies RMS normalization to the input tensor.
+        Args:
+            x: KerasTensor. Input tensor of shape (batch_size, input_dim).
+        Returns:
+            KerasTensor: The RMS-normalized tensor of the same shape (batch_size, input_dim),
+            scaled by the learned `scale` parameter.
+        """
+        x = ops.cast(x, float)
+        rrms = ops.rsqrt(ops.mean(ops.square(x), axis=-1, keepdims=True) + 1e-6)
+        return (x * rrms) * self.scale

{keras_hub_nightly-0.16.1.dev202410200345 → keras_hub_nightly-0.19.0.dev202412070351}/keras_hub/src/layers/modeling/transformer_encoder.py

@@ -170,7 +170,12 @@ class TransformerEncoder(keras.layers.Layer):
         self.built = True
 
     def call(
-        self, inputs, padding_mask=None, attention_mask=None, training=None
+        self,
+        inputs,
+        padding_mask=None,
+        attention_mask=None,
+        training=None,
+        return_attention_scores=False,
     ):
         """Forward pass of the TransformerEncoder.
 
@@ -185,6 +190,7 @@ class TransformerEncoder(keras.layers.Layer):
                 [batch_size, sequence_length, sequence_length].
             training: a boolean indicating whether the layer should behave in
                 training mode or in inference mode.
+            return_attention_scores: a boolean indicating whether the output should be `(attention_output, attention_scores)` if `True` or `attention_output` if `False`. Defaults to `False`.
 
         Returns:
             A Tensor of the same shape as the `inputs`.
@@ -200,12 +206,23 @@ class TransformerEncoder(keras.layers.Layer):
         residual = x
         if self.normalize_first:
             x = self._self_attention_layer_norm(x)
-        x = self._self_attention_layer(
-            query=x,
-            value=x,
-            attention_mask=self_attention_mask,
-            training=training,
-        )
+
+        if return_attention_scores:
+            x, attention_scores = self._self_attention_layer(
+                query=x,
+                value=x,
+                attention_mask=self_attention_mask,
+                return_attention_scores=return_attention_scores,
+                training=training,
+            )
+        else:
+            x = self._self_attention_layer(
+                query=x,
+                value=x,
+                attention_mask=self_attention_mask,
+                training=training,
+            )
+
         x = self._self_attention_dropout(x, training=training)
         x = x + residual
         if not self.normalize_first:
@@ -222,6 +239,9 @@ class TransformerEncoder(keras.layers.Layer):
         if not self.normalize_first:
             x = self._feedforward_layer_norm(x)
 
+        if return_attention_scores:
+            return x, attention_scores
+
         return x
 
     def get_config(self):

{keras_hub_nightly-0.16.1.dev202410200345 → keras_hub_nightly-0.19.0.dev202412070351}/keras_hub/src/layers/preprocessing/image_converter.py

@@ -164,6 +164,11 @@ class ImageConverter(PreprocessingLayer):
         # If inputs are not a tensor type, return a numpy array.
         # This might happen when running under tf.data.
         if ops.is_tensor(inputs):
+            # preprocessing decorator moves tensors to cpu in torch backend and
+            # processed on CPU, and then converted back to the appropriate
+            # device (potentially GPU) after preprocessing.
+            if keras.backend.backend() == "torch" and self.image_size is None:
+                return ops.expand_dims(value, broadcast_dims).cpu()
             return ops.expand_dims(value, broadcast_dims)
         else:
             return np.expand_dims(value, broadcast_dims)

{keras_hub_nightly-0.16.1.dev202410200345 → keras_hub_nightly-0.19.0.dev202412070351}/keras_hub/src/models/albert/albert_presets.py

@@ -8,9 +8,7 @@ backbone_presets = {
                 "Trained on English Wikipedia + BooksCorpus."
             ),
             "params": 11683584,
-            "official_name": "ALBERT",
             "path": "albert",
-            "model_card": "https://github.com/google-research/albert/blob/master/README.md",
         },
         "kaggle_handle": "kaggle://keras/albert/keras/albert_base_en_uncased/2",
     },
@@ -21,9 +19,7 @@ backbone_presets = {
                 "Trained on English Wikipedia + BooksCorpus."
             ),
             "params": 17683968,
-            "official_name": "ALBERT",
             "path": "albert",
-            "model_card": "https://github.com/google-research/albert/blob/master/README.md",
         },
         "kaggle_handle": "kaggle://keras/albert/keras/albert_large_en_uncased/2",
     },
@@ -34,9 +30,7 @@ backbone_presets = {
                 "Trained on English Wikipedia + BooksCorpus."
             ),
             "params": 58724864,
-            "official_name": "ALBERT",
             "path": "albert",
-            "model_card": "https://github.com/google-research/albert/blob/master/README.md",
         },
         "kaggle_handle": "kaggle://keras/albert/keras/albert_extra_large_en_uncased/2",
     },
@@ -47,9 +41,7 @@ backbone_presets = {
                 "Trained on English Wikipedia + BooksCorpus."
             ),
             "params": 222595584,
-            "official_name": "ALBERT",
             "path": "albert",
-            "model_card": "https://github.com/google-research/albert/blob/master/README.md",
         },
         "kaggle_handle": "kaggle://keras/albert/keras/albert_extra_extra_large_en_uncased/2",
     },

{keras_hub_nightly-0.16.1.dev202410200345 → keras_hub_nightly-0.19.0.dev202412070351}/keras_hub/src/models/bart/bart_presets.py

@@ -8,9 +8,7 @@ backbone_presets = {
                 "Trained on BookCorpus, English Wikipedia and CommonCrawl."
             ),
             "params": 139417344,
-            "official_name": "BART",
             "path": "bart",
-            "model_card": "https://github.com/facebookresearch/fairseq/blob/main/examples/bart/README.md",
         },
         "kaggle_handle": "kaggle://keras/bart/keras/bart_base_en/2",
     },
@@ -21,9 +19,7 @@ backbone_presets = {
                 "Trained on BookCorpus, English Wikipedia and CommonCrawl."
             ),
             "params": 406287360,
-            "official_name": "BART",
             "path": "bart",
-            "model_card": "https://github.com/facebookresearch/fairseq/blob/main/examples/bart/README.md",
         },
         "config": {
             "vocabulary_size": 50265,
@@ -43,9 +39,7 @@ backbone_presets = {
                 "summarization dataset."
             ),
             "params": 406287360,
-            "official_name": "BART",
             "path": "bart",
-            "model_card": "https://github.com/facebookresearch/fairseq/blob/main/examples/bart/README.md",
         },
         "config": {
             "vocabulary_size": 50264,