keras-hub-nightly 0.22.0.dev202506170415__py3-none-any.whl → 0.22.0.dev202506190413__py3-none-any.whl

keras_hub/src/layers/modeling/transformer_encoder.py

@@ -16,9 +16,12 @@ class TransformerEncoder(keras.layers.Layer):
     paper [Attention is All You Need](https://arxiv.org/abs/1706.03762). Users
     can instantiate multiple instances of this class to stack up an encoder.
 
-    This layer will correctly compute an attention mask from an implicit
-    Keras padding mask (for example, by passing `mask_zero=True` to a
-    `keras.layers.Embedding` layer). See the Masking and Padding
+    This layer will compute an attention mask, prioritizing explicitly provided
+    masks (a `padding_mask` or a custom `attention_mask`) over an implicit Keras
+    padding mask (for example, by passing `mask_zero=True` to a
+    `keras.layers.Embedding` layer). If both a `padding_mask` and a
+    `attention_mask` are provided, they will be combined to determine the final
+    mask. See the Masking and Padding
     [guide](https://keras.io/guides/understanding_masking_and_padding/)
     for more details.
 

keras_hub/src/models/pali_gemma/pali_gemma_causal_lm.py

@@ -48,7 +48,7 @@ class PaliGemmaCausalLM(CausalLM):
     pali_gemma_lm.generate(
       {
         "images": image,
-        "text": ["answer en where is the cow standing?\\n"]
+        "prompts": ["answer en where is the cow standing?\\n"]
       }
     )
 
@@ -56,7 +56,7 @@ class PaliGemmaCausalLM(CausalLM):
     pali_gemma_lm.generate(
       {
         "images": [image, image],
-        "text": ["answer en where is the cow standing?\\n", "caption en\\n"]
+        "prompts": ["answer en where is the cow standing?\\n", "caption en\\n"]
       }
     )
     ```

keras_hub/src/models/qwen3/qwen3_attention.py

@@ -299,7 +299,7 @@ class Qwen3Attention(keras.layers.Layer):
             attention_scores,
             ops.cast(self._inv_norm_factor, self.compute_dtype),
         )
-        if not self.sliding_window_size:
+        if self.sliding_window_size:
             attention_mask = self._mask_sliding_window(
                 attention_mask,
                 cache_update_index=cache_update_index

keras_hub/src/utils/preset_utils.py

@@ -1,5 +1,6 @@
 import collections
 import datetime
+import glob
 import inspect
 import json
 import os
@@ -317,7 +318,8 @@ def _validate_backbone(preset):
         )
 
     weights_path = os.path.join(preset, MODEL_WEIGHTS_FILE)
-    if not os.path.exists(weights_path):
+    sharded_weights_path = os.path.join(preset, "model_*.weights.h5")
+    if not os.path.exists(weights_path) and not glob.glob(sharded_weights_path):
         raise FileNotFoundError(
             f"The weights file is missing from the preset directory `{preset}`."
         )

keras_hub/src/version.py

@@ -1,7 +1,7 @@
 from keras_hub.src.api_export import keras_hub_export
 
 # Unique source of truth for the version number.
-__version__ = "0.22.0.dev202506170415"
+__version__ = "0.22.0.dev202506190413"
 
 
 @keras_hub_export("keras_hub.version")

{keras_hub_nightly-0.22.0.dev202506170415.dist-info → keras_hub_nightly-0.22.0.dev202506190413.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: keras-hub-nightly
-Version: 0.22.0.dev202506170415
+Version: 0.22.0.dev202506190413
 Summary: Pretrained models for Keras.
 Author-email: Keras team <keras-users@googlegroups.com>
 License-Expression: Apache-2.0

{keras_hub_nightly-0.22.0.dev202506170415.dist-info → keras_hub_nightly-0.22.0.dev202506190413.dist-info}/RECORD

@@ -5,7 +5,7 @@ keras_hub/models/__init__.py,sha256=7MhCw7S-uIPcko-R6g5a-Jy1idKe7BwlI836PfekhHc,
 keras_hub/samplers/__init__.py,sha256=aFQIkiqbZpi8vjrPp2MVII4QUfE-eQjra5fMeHsoy7k,886
 keras_hub/src/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/api_export.py,sha256=9pQZK27JObxWZ96QPLBp1OBsjWigh1iuV6RglPGMRk0,1499
-keras_hub/src/version.py,sha256=aqKaVRKwTfHoj191TVe6s4SnLKcK9G9cIXxCPzQ0ZPs,222
+keras_hub/src/version.py,sha256=hpZsLxPCuYMUHCNKCGUlN2_K9e932CkQVY7nWCBsXB0,222
 keras_hub/src/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/layers/modeling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/layers/modeling/alibi_bias.py,sha256=1XBTHI52L_iJDhN_w5ydu_iMhCuTgQAxEPwcLA6BPuk,4411
@@ -22,7 +22,7 @@ keras_hub/src/layers/modeling/rotary_embedding.py,sha256=BuMD2dCyZi73Eokddx8Q9cF
 keras_hub/src/layers/modeling/sine_position_encoding.py,sha256=NAPW9HaVTMNZgUJNzA3l1B3C_FNvaY7IW-5tQgFgnNg,3453
 keras_hub/src/layers/modeling/token_and_position_embedding.py,sha256=Q-MhVHZSd_W2eWjDCj-s7wo3z8UHmgZ-7j7hElkaXBQ,5263
 keras_hub/src/layers/modeling/transformer_decoder.py,sha256=50KLxaZwaQglWIcFotx3BFh6RwCMXRvGZNXHQBrJ5KM,21172
-keras_hub/src/layers/modeling/transformer_encoder.py,sha256=Qe19_aR6w4PTFbzvBmSP8-ggiAuOJcgCzaJWcjdzA9c,10625
+keras_hub/src/layers/modeling/transformer_encoder.py,sha256=kKPGfjpdhqGJs4MmRyx7fk9xU_2TAS-gLGhq9FZdU0w,10828
 keras_hub/src/layers/modeling/transformer_layer_utils.py,sha256=FuznrW33iG50B-VDN8R1RjuA5JG72yNMJ1TBgWLxR0E,3487
 keras_hub/src/layers/preprocessing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/layers/preprocessing/audio_converter.py,sha256=YGh_kQw65a1Z6S5zzSNVP-ChyLYHq3-eOYpOS53xIN8,4156
@@ -294,7 +294,7 @@ keras_hub/src/models/opt/opt_presets.py,sha256=LrjgI5gbq4Cvfl_pmeCnKn4hS_V_0GYTe
 keras_hub/src/models/opt/opt_tokenizer.py,sha256=oDHeed4xf07tm14hj_C78BkzMuuRwRP2cRHmqYnObrs,2557
 keras_hub/src/models/pali_gemma/__init__.py,sha256=uODWTlttOOchcTLpiYHCEWMXnDxIz8ZVIeYFQN2bd8o,288
 keras_hub/src/models/pali_gemma/pali_gemma_backbone.py,sha256=e1KAg4bmK1PrmYW-Ewx3vD7S2DlX9K8LmbRwv30VEkA,13643
-keras_hub/src/models/pali_gemma/pali_gemma_causal_lm.py,sha256=AViEs6YltUqWnIVo7J02JkXcanBgLSdwZwF56TVr8gc,11345
+keras_hub/src/models/pali_gemma/pali_gemma_causal_lm.py,sha256=aT075qRyFmuo5JwphKkjLt7iJ8BK8NGt-5mqfgIXYqs,11351
 keras_hub/src/models/pali_gemma/pali_gemma_causal_lm_preprocessor.py,sha256=F57y0fZ0wYYxfGIjfrJc1W9uQpViYFx5bvFjj5CqUbI,4814
 keras_hub/src/models/pali_gemma/pali_gemma_decoder_block.py,sha256=24ABQ1vGlppV-KfWh0YqJjzM_Lu2GIwvyJ4X2XXie_A,5616
 keras_hub/src/models/pali_gemma/pali_gemma_image_converter.py,sha256=5yM_jUtrFsWIieiwfFBoP7mtPmQAwywkeLKbd7fhmzk,371
@@ -320,7 +320,7 @@ keras_hub/src/models/qwen/qwen_decoder.py,sha256=utmAvZlU7_nP-6pjGPDinK4JaMzsQSw
 keras_hub/src/models/qwen/qwen_layernorm.py,sha256=DS35r3qd6g5ocL7Nhf_vNzLLMo1aI9VCSmL64dgNOYI,924
 keras_hub/src/models/qwen/qwen_presets.py,sha256=1FkKV6M3yqJz4EP1xa7bEvfIQ721xXT-_ikjWX0xvww,1992
 keras_hub/src/models/qwen/qwen_tokenizer.py,sha256=LCv3IyiDDHqVnM9N3lf5-BE3iwicIh0nKS1hjoPw9lE,1532
-keras_hub/src/models/qwen3/qwen3_attention.py,sha256=sewLjli290XvJ1efGZJEAYqUZfRll7cmhu0258s4C48,13042
+keras_hub/src/models/qwen3/qwen3_attention.py,sha256=mq2Tak0PTItkNi5LnYVcNznS61D2Cdz1-9a-WC7Vw68,13038
 keras_hub/src/models/qwen3/qwen3_backbone.py,sha256=Ylpk_rRWWRxy8irlAPjJU-YrxYGpo8c9lSEO1zZl4gU,7456
 keras_hub/src/models/qwen3/qwen3_causal_lm_preprocessor.py,sha256=H4g-bgvuhAUnDwjJovydK16Kes38ZFZWPvflrgHqZis,458
 keras_hub/src/models/qwen3/qwen3_decoder.py,sha256=68s9jQj53zFmXE4-SGXKYHu546fXOyi9LUbnKk-HGYY,11595
@@ -482,7 +482,7 @@ keras_hub/src/tokenizers/word_piece_tokenizer_trainer.py,sha256=cylrs02ZrYQ1TuZr
 keras_hub/src/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/utils/keras_utils.py,sha256=2qrh4F-rqceVFSx0-cbsFBfWae5hBXFb_sEtPPcImf4,4628
 keras_hub/src/utils/pipeline_model.py,sha256=jgzB6NQPSl0KOu08N-TazfOnXnUJbZjH2EXXhx25Ftg,9084
-keras_hub/src/utils/preset_utils.py,sha256=p1N62tK0H_z-WH9XWcpq0UPEkd4po59LvcE2k-KVg1Y,34853
+keras_hub/src/utils/preset_utils.py,sha256=GKYFKK9YcdIrMm0_hC_KTIXgpiMYD6SauMnSRpNsDQo,34975
 keras_hub/src/utils/python_utils.py,sha256=N8nWeO3san4YnGkffRXG3Ix7VEIMTKSN21FX5TuL7G8,202
 keras_hub/src/utils/tensor_utils.py,sha256=WrohV6-hvxtLE6rRRhtN4hy8GkHikV-NrRnVEYUwJQo,16133
 keras_hub/src/utils/coco/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -517,7 +517,7 @@ keras_hub/src/utils/transformers/preset_loader.py,sha256=K5FzDAtCuXS9rmZc0Zj7UCw
 keras_hub/src/utils/transformers/safetensor_utils.py,sha256=CYUHyA4y-B61r7NDnCsFb4t_UmSwZ1k9L-8gzEd6KRg,3339
 keras_hub/tokenizers/__init__.py,sha256=uMjjm0mzUkRb0e4Ac_JK8aJ9cKGUi5UqmzWoWAFJprE,4164
 keras_hub/utils/__init__.py,sha256=jXPqVGBpJr_PpYmqD8aDG-fRMlxH-ulqCR2SZMn288Y,646
-keras_hub_nightly-0.22.0.dev202506170415.dist-info/METADATA,sha256=iVujX8QDS3ZBEO3R7iU4WfhqfkXVVXk39_GbDGkLZPw,7393
-keras_hub_nightly-0.22.0.dev202506170415.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-keras_hub_nightly-0.22.0.dev202506170415.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
-keras_hub_nightly-0.22.0.dev202506170415.dist-info/RECORD,,
+keras_hub_nightly-0.22.0.dev202506190413.dist-info/METADATA,sha256=aeqbPu3SMybWNG4VWxkrFr3sWR4IhshHN5wJCLfJ4mQ,7393
+keras_hub_nightly-0.22.0.dev202506190413.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+keras_hub_nightly-0.22.0.dev202506190413.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
+keras_hub_nightly-0.22.0.dev202506190413.dist-info/RECORD,,