keras-hub-nightly 0.16.1.dev202410020340__py3-none-any.whl → 0.19.0.dev202501260345__py3-none-any.whl

keras_hub/src/models/electra/electra_presets.py

@@ -8,11 +8,9 @@ backbone_presets = {
                 "lowercased. Trained on English Wikipedia + BooksCorpus."
             ),
             "params": 13548800,
-            "official_name": "ELECTRA",
             "path": "electra",
-            "model_card": "https://github.com/google-research/electra",
         },
-        "kaggle_handle": "kaggle://keras/electra/keras/electra_small_discriminator_uncased_en/1",
+        "kaggle_handle": "kaggle://keras/electra/keras/electra_small_discriminator_uncased_en/2",
     },
     "electra_small_generator_uncased_en": {
         "metadata": {
@@ -21,11 +19,9 @@ backbone_presets = {
                 "lowercased. Trained on English Wikipedia + BooksCorpus."
             ),
             "params": 13548800,
-            "official_name": "ELECTRA",
             "path": "electra",
-            "model_card": "https://github.com/google-research/electra",
         },
-        "kaggle_handle": "kaggle://keras/electra/keras/electra_small_generator_uncased_en/1",
+        "kaggle_handle": "kaggle://keras/electra/keras/electra_small_generator_uncased_en/2",
     },
     "electra_base_discriminator_uncased_en": {
         "metadata": {
@@ -34,11 +30,9 @@ backbone_presets = {
                 "lowercased. Trained on English Wikipedia + BooksCorpus."
             ),
             "params": 109482240,
-            "official_name": "ELECTRA",
             "path": "electra",
-            "model_card": "https://github.com/google-research/electra",
         },
-        "kaggle_handle": "kaggle://keras/electra/keras/electra_base_discriminator_uncased_en/1",
+        "kaggle_handle": "kaggle://keras/electra/keras/electra_base_discriminator_uncased_en/2",
     },
     "electra_base_generator_uncased_en": {
         "metadata": {
@@ -47,11 +41,9 @@ backbone_presets = {
                 "lowercased. Trained on English Wikipedia + BooksCorpus."
             ),
             "params": 33576960,
-            "official_name": "ELECTRA",
             "path": "electra",
-            "model_card": "https://github.com/google-research/electra",
         },
-        "kaggle_handle": "kaggle://keras/electra/keras/electra_base_generator_uncased_en/1",
+        "kaggle_handle": "kaggle://keras/electra/keras/electra_base_generator_uncased_en/2",
     },
     "electra_large_discriminator_uncased_en": {
         "metadata": {
@@ -60,11 +52,9 @@ backbone_presets = {
                 "lowercased. Trained on English Wikipedia + BooksCorpus."
             ),
             "params": 335141888,
-            "official_name": "ELECTRA",
             "path": "electra",
-            "model_card": "https://github.com/google-research/electra",
         },
-        "kaggle_handle": "kaggle://keras/electra/keras/electra_large_discriminator_uncased_en/1",
+        "kaggle_handle": "kaggle://keras/electra/keras/electra_large_discriminator_uncased_en/2",
     },
     "electra_large_generator_uncased_en": {
         "metadata": {
@@ -73,10 +63,8 @@ backbone_presets = {
                 "lowercased. Trained on English Wikipedia + BooksCorpus."
             ),
             "params": 51065344,
-            "official_name": "ELECTRA",
             "path": "electra",
-            "model_card": "https://github.com/google-research/electra",
         },
-        "kaggle_handle": "kaggle://keras/electra/keras/electra_large_generator_uncased_en/1",
+        "kaggle_handle": "kaggle://keras/electra/keras/electra_large_generator_uncased_en/2",
     },
 }

keras_hub/src/models/f_net/f_net_presets.py

@@ -8,11 +8,9 @@ backbone_presets = {
                 "Trained on the C4 dataset."
             ),
             "params": 82861056,
-            "official_name": "FNet",
             "path": "f_net",
-            "model_card": "https://github.com/google-research/google-research/blob/master/f_net/README.md",
         },
-        "kaggle_handle": "kaggle://keras/f_net/keras/f_net_base_en/2",
+        "kaggle_handle": "kaggle://keras/f_net/keras/f_net_base_en/3",
     },
     "f_net_large_en": {
         "metadata": {
@@ -21,10 +19,8 @@ backbone_presets = {
                 "Trained on the C4 dataset."
             ),
             "params": 236945408,
-            "official_name": "FNet",
             "path": "f_net",
-            "model_card": "https://github.com/google-research/google-research/blob/master/f_net/README.md",
         },
-        "kaggle_handle": "kaggle://keras/f_net/keras/f_net_large_en/2",
+        "kaggle_handle": "kaggle://keras/f_net/keras/f_net_large_en/3",
     },
 }

keras_hub/src/models/f_net/f_net_text_classifier.py

@@ -34,9 +34,9 @@ class FNetTextClassifier(TextClassifier):
     Args:
         backbone: A `keras_hub.models.FNetBackbone` instance.
         num_classes: int. Number of classes to predict.
-        preprocessor: A `keras_hub.models.FNetTextClassifierPreprocessor` or `None`. If
-            `None`, this model will not apply preprocessing, and inputs should
-            be preprocessed before calling the model.
+        preprocessor: A `keras_hub.models.FNetTextClassifierPreprocessor` or
+            `None`. If `None`, this model will not apply preprocessing, and
+            inputs should be preprocessed before calling the model.
         activation: Optional `str` or callable. The
             activation function to use on the model outputs. Set
             `activation="softmax"` to return output probabilities.

keras_hub/src/models/f_net/f_net_text_classifier_preprocessor.py

@@ -22,9 +22,9 @@ class FNetTextClassifierPreprocessor(TextClassifierPreprocessor):
 
      1. Tokenize any number of input segments using the `tokenizer`.
      2. Pack the inputs together using a `keras_hub.layers.MultiSegmentPacker`.
-       with the appropriate `"[CLS]"`, `"[SEP]"` and `"<pad>"` tokens.
-     3. Construct a dictionary with keys `"token_ids"`, and `"segment_ids"`  that
-       can be passed directly to `keras_hub.models.FNetBackbone`.
+        with the appropriate `"[CLS]"`, `"[SEP]"` and `"<pad>"` tokens.
+     3. Construct a dictionary with keys `"token_ids"`, and `"segment_ids"`
+        that can be passed directly to `keras_hub.models.FNetBackbone`.
 
     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_hub/src/models/falcon/falcon_backbone.py

@@ -20,15 +20,17 @@ class FalconBackbone(Backbone):
     Args:
         vocabulary_size: int. The size of the token vocabulary.
         num_layers: int. The number of transformer layers.
-        num_attention_heads: int. The number of attention heads for each transformer.
-            The hidden size must be divisible by the number of attention heads.
+        num_attention_heads: int. The number of attention heads for each
+            transformer. The hidden size must be divisible by the number of
+            attention heads.
         hidden_dim: int. The dimensionality of the embeddings and hidden states.
         intermediate_dim: int. The output dimension of the first Dense layer in
             the MLP network of each transformer.
         layer_norm_epsilon: float. Epsilon for the layer normalization layers in
             the transformer decoder.
         attention_dropout_rate: float. Dropout probability for the attention.
-        feedforward_dropout_rate: flaot. Dropout probability for the feedforward.
+        feedforward_dropout_rate: flaot. Dropout probability for the
+            feedforward.
         dtype: string or `keras.mixed_precision.DTypePolicy`. The dtype to use
             for model computations and weights. Note that some computations,
             such as softmax and layer normalization, will always be done at

keras_hub/src/models/falcon/falcon_causal_lm.py

@@ -40,7 +40,9 @@ class FalconCausalLM(CausalLM):
 
     Use `generate()` to do text generation.
     ```python
-    falcon_lm = keras_hub.models.FalconCausalLM.from_preset("falcon_refinedweb_1b_en")
+    falcon_lm = keras_hub.models.FalconCausalLM.from_preset(
+        "falcon_refinedweb_1b_en"
+    )
     falcon_lm.generate("I want to say", max_length=30)
 
     # Generate with batched prompts.
@@ -49,7 +51,9 @@ class FalconCausalLM(CausalLM):
 
     Compile the `generate()` function with a custom sampler.
     ```python
-    falcon_lm = keras_hub.models.FalconCausalLM.from_preset("falcon_refinedweb_1b_en")
+    falcon_lm = keras_hub.models.FalconCausalLM.from_preset(
+        "falcon_refinedweb_1b_en"
+    )
     falcon_lm.compile(sampler="top_k")
     falcon_lm.generate("I want to say", max_length=30)
 
@@ -60,7 +64,8 @@ class FalconCausalLM(CausalLM):
     Use `generate()` without preprocessing.
     ```python
     prompt = {
-        # Token ids for "<|endoftext|> Keras is".
+        # Token ids for
+        # "<|endoftext|> Keras is".
         "token_ids": np.array([[50256, 17337,   292,   318]] * 2),
         # Use `"padding_mask"` to indicate values that should not be overridden.
         "padding_mask": np.array([[1, 1, 1, 1]] * 2),
@@ -76,15 +81,20 @@ class FalconCausalLM(CausalLM):
     Call `fit()` on a single batch.
     ```python
     features = ["The quick brown fox jumped.", "I forgot my homework."]
-    falcon_lm = keras_hub.models.FalconCausalLM.from_preset("falcon_refinedweb_1b_en")
+    falcon_lm = keras_hub.models.FalconCausalLM.from_preset(
+        "falcon_refinedweb_1b_en"
+    )
     falcon_lm.fit(x=features, batch_size=2)
     ```
 
     Call `fit()` without preprocessing.
     ```python
     x = {
-        # Token ids for "<|endoftext|> Keras is deep learning library<|endoftext|>"
-        "token_ids": np.array([[50256, 17337,   292,   318,  2769,  4673,  5888, 50256, 0]] * 2),
+        # Token ids for
+        # "<|endoftext|> Keras is deep learning library<|endoftext|>"
+        "token_ids": np.array(
+            [[50256, 17337, 292, 318, 2769,4673,5888, 50256, 0]] * 2
+        ),
         "padding_mask": np.array([[1, 1, 1, 1, 1, 1, 1, 1, 0]] * 2),
     }
     y = np.array([[17337,   292,   318,  2769,  4673,  5888, 50256, 0, 0]] * 2)
@@ -164,8 +174,8 @@ class FalconCausalLM(CausalLM):
         Args:
             token_ids: a dense int Tensor with shape `(batch_size, max_length)`.
             cache: a dense float Tensor, the cache of key and value.
-            cache_update_index: int, or int Tensor. The index of current inputs in the
-                whole sequence.
+            cache_update_index: int, or int Tensor. The index of current inputs
+                in the whole sequence.
 
         Returns:
             A (logits, hidden_states, cache) tuple. Where `logits` is the

keras_hub/src/models/falcon/falcon_presets.py

@@ -8,10 +8,8 @@ backbone_presets = {
                 "350B tokens of RefinedWeb dataset."
             ),
             "params": 1311625216,
-            "official_name": "Falcon",
             "path": "falcon",
-            "model_card": "https://huggingface.co/tiiuae/falcon-rw-1b",
         },
-        "kaggle_handle": "kaggle://keras/falcon/keras/falcon_refinedweb_1b_en/1",
+        "kaggle_handle": "kaggle://keras/falcon/keras/falcon_refinedweb_1b_en/2",
     },
 }

keras_hub/src/models/falcon/falcon_tokenizer.py

@@ -36,7 +36,9 @@ class FalconTokenizer(BytePairTokenizer):
 
     ```python
     # Unbatched input.
-    tokenizer = keras_hub.models.FalconTokenizer.from_preset("falcon_refinedweb_1b_en")
+    tokenizer = keras_hub.models.FalconTokenizer.from_preset(
+        "falcon_refinedweb_1b_en"
+    )
     tokenizer("The quick brown fox jumped.")
 
     # Batched input.
@@ -49,7 +51,10 @@ class FalconTokenizer(BytePairTokenizer):
     vocab = {"<|endoftext|>": 0, "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.FalconTokenizer(vocabulary=vocab, merges=merges)
+    tokenizer = keras_hub.models.FalconTokenizer(
+        vocabulary=vocab,
+        merges=merges,
+    )
     tokenizer("a quick fox.")
     ```
     """

keras_hub/src/models/feature_pyramid_backbone.py

@@ -15,7 +15,7 @@ class FeaturePyramidBackbone(Backbone):
     Example:
 
     ```python
-    input_data = np.random.uniform(0, 255, size=(2, 224, 224, 3))
+    input_data = np.random.uniform(0, 256, size=(2, 224, 224, 3))
 
     # Convert to feature pyramid output format using ResNet.
     backbone = ResNetBackbone.from_preset("resnet50")

keras_hub/src/models/flux/__init__.py

@@ -0,0 +1,5 @@
+from keras_hub.src.models.flux.flux_model import FluxBackbone
+from keras_hub.src.models.flux.flux_presets import presets
+from keras_hub.src.utils.preset_utils import register_presets
+
+register_presets(presets, FluxBackbone)