keras-hub 0.25.0__py3-none-any.whl → 0.25.1__py3-none-any.whl

keras_hub/src/models/gemma3/gemma3_decoder_block.py

@@ -251,6 +251,11 @@ class Gemma3DecoderBlock(keras.layers.Layer):
         cache_update_mask=None,
     ):
         # Note: `vision_mask` is used only for Gemma3.
+        # If float16, we clamp the input to avoid overflow.
+        is_float16 = keras.backend.standardize_dtype(x.dtype) == "float16"
+        if is_float16:
+            x = ops.clip(x, -65504, 65504)
+
         normalized_x = self.pre_attention_norm(x)
         attention_mask = self._compute_attention_mask(
             normalized_x, padding_mask, vision_mask, cache, cache_update_index
@@ -275,7 +280,15 @@ class Gemma3DecoderBlock(keras.layers.Layer):
         if self.dropout:
             attention = self.attention_dropout(attention)
 
-        attention_x = x + attention
+        if is_float16:
+            attention_x = ops.add(
+                ops.cast(x, "float32"), ops.cast(attention, "float32")
+            )
+            attention_x = ops.clip(attention_x, -65504, 65504)
+            attention_x = ops.cast(attention_x, "float16")
+        else:
+            attention_x = x + attention
+
         normalized_x = self.pre_ffw_norm(attention_x)
 
         x1 = self.gating_ffw(normalized_x)
@@ -286,7 +299,14 @@ class Gemma3DecoderBlock(keras.layers.Layer):
         if self.use_post_ffw_norm:
             x = self.post_ffw_norm(x)
 
-        x = x + attention_x
+        if is_float16:
+            x = ops.add(
+                ops.cast(x, "float32"), ops.cast(attention_x, "float32")
+            )
+            x = ops.clip(x, -65504, 65504)
+            x = ops.cast(x, "float16")
+        else:
+            x = x + attention_x
 
         if cache is not None:
             return x, new_cache

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__ = "0.25.0"
+__version__ = "0.25.1"
 
 
 @keras_hub_export("keras_hub.version")

{keras_hub-0.25.0.dist-info → keras_hub-0.25.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: keras-hub
-Version: 0.25.0
+Version: 0.25.1
 Summary: Pretrained models for Keras.
 Author-email: Keras team <keras-users@googlegroups.com>
 License-Expression: Apache-2.0

{keras_hub-0.25.0.dist-info → keras_hub-0.25.1.dist-info}/RECORD

@@ -5,7 +5,7 @@ keras_hub/models/__init__.py,sha256=-RPLKDEOnRJmHyB867IApKj98hBrhUIuGtO15xYKQxw,
 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=rshx76XoLXH7RCuRIo37RPFdGafttvDLFxgeDxJX22E,206
+keras_hub/src/version.py,sha256=WSC-QBbLh3MiIyJz2ADMs5o4B5gmc1jUEKu6olCr_hI,206
 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
@@ -249,7 +249,7 @@ keras_hub/src/models/gemma3/gemma3_attention.py,sha256=u3RNI8dva5lzzqFNTAe9996s8
 keras_hub/src/models/gemma3/gemma3_backbone.py,sha256=HdWDRuF9MMwIzNVZEd1j53ILzptskvCxFiO__nfVQYU,16686
 keras_hub/src/models/gemma3/gemma3_causal_lm.py,sha256=U3C9TWlIz8VefAxQ0wJ6bDz18wqHBie8B26Ub_nFZs4,13843
 keras_hub/src/models/gemma3/gemma3_causal_lm_preprocessor.py,sha256=_gvKPoXqNXpXcsfc8L29wW50MToHIr2D-4Q6MNVfBU0,29790
-keras_hub/src/models/gemma3/gemma3_decoder_block.py,sha256=CYwYazqwakLNfhOLBl_8Q2TVZcMcOxMtiZtuVlk_hoo,11470
+keras_hub/src/models/gemma3/gemma3_decoder_block.py,sha256=IBfi724Vwtq1vjuoShEEy-WpL8zyiUqeHwg1IVCSehU,12191
 keras_hub/src/models/gemma3/gemma3_image_converter.py,sha256=czi5JrTyKiK0nFzvonviBIX8jjvLHqvGNA9RyheB31k,536
 keras_hub/src/models/gemma3/gemma3_interleave_embeddings.py,sha256=CfYdudk5En9iU6vEnrcrEWIztloD1r8VzF2extqAhAM,4616
 keras_hub/src/models/gemma3/gemma3_presets.py,sha256=3jK1OyDKDdSG_lC7yh-8O5BMKJ61knbVrHQgKe0cJiQ,8209
@@ -638,7 +638,7 @@ keras_hub/src/utils/transformers/export/gemma.py,sha256=xX_vfQwvFZ_-lQX4kgMNOGKL
 keras_hub/src/utils/transformers/export/hf_exporter.py,sha256=Qk52c6LIA2eMHUNY9Vy4STJSpnhLMdJ_t-3ljqhSr4k,5081
 keras_hub/tokenizers/__init__.py,sha256=7squHiwAu3KU5rBiupi4pH0zpUg5BwRfAOu0JcJmfA4,4873
 keras_hub/utils/__init__.py,sha256=jXPqVGBpJr_PpYmqD8aDG-fRMlxH-ulqCR2SZMn288Y,646
-keras_hub-0.25.0.dist-info/METADATA,sha256=XcP71H-itOfJNo_jV_WxUacUFlRLho27ZzLzltHwuns,7371
-keras_hub-0.25.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-keras_hub-0.25.0.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
-keras_hub-0.25.0.dist-info/RECORD,,
+keras_hub-0.25.1.dist-info/METADATA,sha256=uzKpDD4OSxVV5X4qPqBWXg11o6G11LhSs_z0F7t7woU,7371
+keras_hub-0.25.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+keras_hub-0.25.1.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
+keras_hub-0.25.1.dist-info/RECORD,,