keras-hub-nightly 0.21.0.dev202505200408__py3-none-any.whl → 0.21.0.dev202505230409__py3-none-any.whl

keras_hub/src/models/gemma/gemma_presets.py

@@ -61,7 +61,7 @@ backbone_presets = {
             "params": 8537680896,
             "path": "gemma",
         },
-        "kaggle_handle": "kaggle://keras/gemma/keras/gemma_7b_en/3",
+        "kaggle_handle": "kaggle://keras/gemma/keras/gemma_7b_en/4",
     },
     "gemma_instruct_7b_en": {
         "metadata": {
@@ -71,7 +71,7 @@ backbone_presets = {
             "params": 8537680896,
             "path": "gemma",
         },
-        "kaggle_handle": "kaggle://keras/gemma/keras/gemma_instruct_7b_en/3",
+        "kaggle_handle": "kaggle://keras/gemma/keras/gemma_instruct_7b_en/4",
     },
     "gemma_1.1_instruct_7b_en": {
         "metadata": {
@@ -82,7 +82,7 @@ backbone_presets = {
             "params": 8537680896,
             "path": "gemma",
         },
-        "kaggle_handle": "kaggle://keras/gemma/keras/gemma_1.1_instruct_7b_en/4",
+        "kaggle_handle": "kaggle://keras/gemma/keras/gemma_1.1_instruct_7b_en/5",
     },
     "code_gemma_7b_en": {
         "metadata": {
@@ -94,7 +94,7 @@ backbone_presets = {
             "params": 8537680896,
             "path": "gemma",
         },
-        "kaggle_handle": "kaggle://keras/codegemma/keras/code_gemma_7b_en/2",
+        "kaggle_handle": "kaggle://keras/codegemma/keras/code_gemma_7b_en/3",
     },
     "code_gemma_instruct_7b_en": {
         "metadata": {
@@ -106,7 +106,7 @@ backbone_presets = {
             "params": 8537680896,
             "path": "gemma",
         },
-        "kaggle_handle": "kaggle://keras/codegemma/keras/code_gemma_instruct_7b_en/2",
+        "kaggle_handle": "kaggle://keras/codegemma/keras/code_gemma_instruct_7b_en/3",
     },
     "code_gemma_1.1_instruct_7b_en": {
         "metadata": {
@@ -118,7 +118,7 @@ backbone_presets = {
             "params": 8537680896,
             "path": "gemma",
         },
-        "kaggle_handle": "kaggle://keras/codegemma/keras/code_gemma_1.1_instruct_7b_en/2",
+        "kaggle_handle": "kaggle://keras/codegemma/keras/code_gemma_1.1_instruct_7b_en/3",
     },
     "gemma2_2b_en": {
         "metadata": {
@@ -144,7 +144,7 @@ backbone_presets = {
             "params": 9241705984,
             "path": "gemma",
         },
-        "kaggle_handle": "kaggle://keras/gemma2/keras/gemma2_9b_en/3",
+        "kaggle_handle": "kaggle://keras/gemma2/keras/gemma2_9b_en/4",
     },
     "gemma2_instruct_9b_en": {
         "metadata": {
@@ -154,7 +154,7 @@ backbone_presets = {
             "params": 9241705984,
             "path": "gemma",
         },
-        "kaggle_handle": "kaggle://keras/gemma2/keras/gemma2_instruct_9b_en/3",
+        "kaggle_handle": "kaggle://keras/gemma2/keras/gemma2_instruct_9b_en/4",
     },
     "gemma2_27b_en": {
         "metadata": {
@@ -162,7 +162,7 @@ backbone_presets = {
             "params": 27227128320,
             "path": "gemma",
         },
-        "kaggle_handle": "kaggle://keras/gemma2/keras/gemma2_27b_en/2",
+        "kaggle_handle": "kaggle://keras/gemma2/keras/gemma2_27b_en/3",
     },
     "gemma2_instruct_27b_en": {
         "metadata": {
@@ -172,7 +172,7 @@ backbone_presets = {
             "params": 27227128320,
             "path": "gemma",
         },
-        "kaggle_handle": "kaggle://keras/gemma2/keras/gemma2_instruct_27b_en/2",
+        "kaggle_handle": "kaggle://keras/gemma2/keras/gemma2_instruct_27b_en/3",
     },
     "shieldgemma_2b_en": {
         "metadata": {

keras_hub/src/models/gemma3/gemma3_presets.py

@@ -55,7 +55,7 @@ backbone_presets = {
             "params": 11765788416,
             "path": "gemma3",
         },
-        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_12b_text/2",
+        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_12b_text/3",
     },
     "gemma3_instruct_12b_text": {
         "metadata": {
@@ -66,7 +66,7 @@ backbone_presets = {
             "params": 11765788416,
             "path": "gemma3",
         },
-        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_instruct_12b_text/2",
+        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_instruct_12b_text/3",
     },
     "gemma3_27b_text": {
         "metadata": {
@@ -77,7 +77,7 @@ backbone_presets = {
             "params": 27009002240,
             "path": "gemma3",
         },
-        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_27b_text/3",
+        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_27b_text/4",
     },
     "gemma3_instruct_27b_text": {
         "metadata": {
@@ -88,7 +88,7 @@ backbone_presets = {
             "params": 27009002240,
             "path": "gemma3",
         },
-        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_instruct_27b_text/2",
+        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_instruct_27b_text/3",
     },
     "gemma3_4b": {
         "metadata": {
@@ -121,7 +121,7 @@ backbone_presets = {
             "params": 12187079280,
             "path": "gemma3",
         },
-        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_12b/1",
+        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_12b/2",
     },
     "gemma3_instruct_12b": {
         "metadata": {
@@ -132,7 +132,7 @@ backbone_presets = {
             "params": 12187079280,
             "path": "gemma3",
         },
-        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_instruct_12b/1",
+        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_instruct_12b/2",
     },
     "gemma3_27b": {
         "metadata": {
@@ -143,7 +143,7 @@ backbone_presets = {
             "params": 27432062576,
             "path": "gemma3",
         },
-        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_27b/1",
+        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_27b/2",
     },
     "gemma3_instruct_27b": {
         "metadata": {
@@ -154,6 +154,6 @@ backbone_presets = {
             "params": 27432062576,
             "path": "gemma3",
         },
-        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_instruct_27b/1",
+        "kaggle_handle": "kaggle://keras/gemma3/keras/gemma3_instruct_27b/2",
     },
 }

keras_hub/src/models/llama/llama_presets.py

@@ -8,7 +8,7 @@ backbone_presets = {
             "params": 6738415616,
             "path": "llama",
         },
-        "kaggle_handle": "kaggle://keras/llama2/keras/llama2_7b_en/2",
+        "kaggle_handle": "kaggle://keras/llama2/keras/llama2_7b_en/3",
     },
     "llama2_7b_en_int8": {
         "metadata": {
@@ -30,7 +30,7 @@ backbone_presets = {
             "params": 6738415616,
             "path": "llama",
         },
-        "kaggle_handle": "kaggle://keras/llama2/keras/llama2_instruct_7b_en/2",
+        "kaggle_handle": "kaggle://keras/llama2/keras/llama2_instruct_7b_en/3",
     },
     "llama2_instruct_7b_en_int8": {
         "metadata": {
@@ -52,6 +52,6 @@ backbone_presets = {
             "params": 6738415616,
             "path": "llama",
         },
-        "kaggle_handle": "kaggle://keras/vicuna/keras/vicuna_1.5_7b_en/2",
+        "kaggle_handle": "kaggle://keras/vicuna/keras/vicuna_1.5_7b_en/3",
     },
 }

keras_hub/src/models/llama3/llama3_presets.py

@@ -8,7 +8,7 @@ backbone_presets = {
             "params": 8030261248,
             "path": "llama3",
         },
-        "kaggle_handle": "kaggle://keras/llama3/keras/llama3_8b_en/4",
+        "kaggle_handle": "kaggle://keras/llama3/keras/llama3_8b_en/5",
     },
     "llama3_8b_en_int8": {
         "metadata": {
@@ -30,7 +30,7 @@ backbone_presets = {
             "params": 8030261248,
             "path": "llama3",
         },
-        "kaggle_handle": "kaggle://keras/llama3/keras/llama3_instruct_8b_en/4",
+        "kaggle_handle": "kaggle://keras/llama3/keras/llama3_instruct_8b_en/5",
     },
     "llama3_instruct_8b_en_int8": {
         "metadata": {

keras_hub/src/models/mistral/mistral_presets.py

@@ -8,7 +8,7 @@ backbone_presets = {
             "params": 7241732096,
             "path": "mistral",
         },
-        "kaggle_handle": "kaggle://keras/mistral/keras/mistral_7b_en/7",
+        "kaggle_handle": "kaggle://keras/mistral/keras/mistral_7b_en/8",
     },
     "mistral_instruct_7b_en": {
         "metadata": {
@@ -16,7 +16,7 @@ backbone_presets = {
             "params": 7241732096,
             "path": "mistral",
         },
-        "kaggle_handle": "kaggle://keras/mistral/keras/mistral_instruct_7b_en/7",
+        "kaggle_handle": "kaggle://keras/mistral/keras/mistral_instruct_7b_en/8",
     },
     "mistral_0.2_instruct_7b_en": {
         "metadata": {
@@ -24,6 +24,6 @@ backbone_presets = {
             "params": 7241732096,
             "path": "mistral",
         },
-        "kaggle_handle": "kaggle://keras/mistral/keras/mistral_0.2_instruct_7b_en/2",
+        "kaggle_handle": "kaggle://keras/mistral/keras/mistral_0.2_instruct_7b_en/3",
     },
 }

keras_hub/src/models/mixtral/mixtral_attention.py

@@ -27,19 +27,19 @@ class CachedMixtralAttention(keras.layers.Layer):
         **kwargs,
     ):
         super().__init__(**kwargs)
-        self._num_query_heads = num_query_heads
-        self._num_key_value_heads = num_key_value_heads
-        self._sliding_window = sliding_window
-        self._dropout = dropout
+        self.num_query_heads = num_query_heads
+        self.num_key_value_heads = num_key_value_heads
+        self.sliding_window = sliding_window
+        self.dropout = dropout
 
-        self._num_key_value_groups = num_query_heads // num_key_value_heads
-        self._rope_max_wavelength = rope_max_wavelength
+        self.num_key_value_groups = num_query_heads // num_key_value_heads
+        self.rope_max_wavelength = rope_max_wavelength
 
         self._kernel_initializer = keras.initializers.get(
             clone_initializer(kernel_initializer)
         )
 
-        self._rope_scaling_factor = rope_scaling_factor
+        self.rope_scaling_factor = rope_scaling_factor
 
     def build(self, inputs_shape):
         # Einsum variables:
@@ -51,12 +51,12 @@ class CachedMixtralAttention(keras.layers.Layer):
         # v = num key/value heads
         # h = head dim
         self._hidden_dim = inputs_shape[-1]
-        self._head_dim = self._hidden_dim // self._num_query_heads
+        self._head_dim = self._hidden_dim // self.num_query_heads
         self._inv_norm_factor = 1.0 / math.sqrt(self._head_dim)
 
         self.query_dense = keras.layers.EinsumDense(
             equation="bqm,muh->bquh",
-            output_shape=(None, self._num_query_heads, self._head_dim),
+            output_shape=(None, self.num_query_heads, self._head_dim),
             kernel_initializer=self._kernel_initializer,
             dtype=self.dtype_policy,
             name="query",
@@ -67,7 +67,7 @@ class CachedMixtralAttention(keras.layers.Layer):
             equation="bkm,mvh->bkvh",
             output_shape=(
                 None,
-                self._num_key_value_heads,
+                self.num_key_value_heads,
                 self._head_dim,
             ),
             kernel_initializer=self._kernel_initializer,
@@ -80,7 +80,7 @@ class CachedMixtralAttention(keras.layers.Layer):
             equation="bkm,mvh->bkvh",
             output_shape=(
                 None,
-                self._num_key_value_heads,
+                self.num_key_value_heads,
                 self._head_dim,
             ),
             kernel_initializer=self._kernel_initializer,
@@ -89,31 +89,31 @@ class CachedMixtralAttention(keras.layers.Layer):
         )
         self.value_dense.build(inputs_shape)
 
-        self._softmax = keras.layers.Softmax(
+        self.softmax = keras.layers.Softmax(
             axis=-1,
             dtype="float32",
             name="attention_softmax",
         )
 
-        self._dropout_layer = keras.layers.Dropout(
-            rate=self._dropout,
+        self.dropout_layer = keras.layers.Dropout(
+            rate=self.dropout,
             dtype=self.dtype_policy,
         )
 
-        self._output_dense = keras.layers.EinsumDense(
+        self.output_dense = keras.layers.EinsumDense(
             equation="bquh,uhm->bqm",
             output_shape=(None, self._hidden_dim),
             kernel_initializer=self._kernel_initializer,
             dtype=self.dtype_policy,
             name="attention_output",
         )
-        self._output_dense.build(
-            (None, None, self._num_query_heads, self._head_dim)
+        self.output_dense.build(
+            (None, None, self.num_query_heads, self._head_dim)
         )
 
         self.rotary_embedding_layer = RotaryEmbedding(
-            max_wavelength=self._rope_max_wavelength,
-            scaling_factor=self._rope_scaling_factor,
+            max_wavelength=self.rope_max_wavelength,
+            scaling_factor=self.rope_scaling_factor,
             dtype=self.dtype_policy,
         )
 
@@ -168,18 +168,18 @@ class CachedMixtralAttention(keras.layers.Layer):
 
         # [batch_shape, seq_len, num_key_value_heads, head_dim]
         # -> [batch_shape, seq_len, num_heads, head_dim]
-        key = ops.repeat(key, repeats=self._num_key_value_groups, axis=2)
-        value = ops.repeat(value, repeats=self._num_key_value_groups, axis=2)
+        key = ops.repeat(key, repeats=self.num_key_value_groups, axis=2)
+        value = ops.repeat(value, repeats=self.num_key_value_groups, axis=2)
 
         attention_output = self._compute_attention(
             query, key, value, attention_mask
         )
 
-        attention_output = self._dropout_layer(
+        attention_output = self.dropout_layer(
             attention_output, training=training
         )
 
-        attention_output = self._output_dense(attention_output)
+        attention_output = self.output_dense(attention_output)
 
         if cache is not None:
             return attention_output, cache
@@ -187,10 +187,8 @@ class CachedMixtralAttention(keras.layers.Layer):
 
     def _masked_softmax(self, attention_scores, attention_mask=None):
         if attention_mask is not None:
-            return self._softmax(
-                attention_scores, attention_mask[:, None, :, :]
-            )
-        return self._softmax(attention_scores)
+            return self.softmax(attention_scores, attention_mask[:, None, :, :])
+        return self.softmax(attention_scores)
 
     def _use_fused_attention_op(self):
         if not fused_attention_op_available():
@@ -198,9 +196,6 @@ class CachedMixtralAttention(keras.layers.Layer):
         if self.dropout > 0.0:
             return False
         if running_on_gpu():
-            # GPU never supports softcap in the fused op.
-            if self.logit_soft_cap is not None:
-                return False
             return gpu_supports_fused_attention_op()
         elif running_on_tpu():
             # TPU supports softcap with on keras >= 3.10.
@@ -215,18 +210,12 @@ class CachedMixtralAttention(keras.layers.Layer):
                 attention_mask = ops.expand_dims(attention_mask, axis=1)
                 attention_mask = ops.cast(attention_mask, dtype="bool")
 
-            if self.logit_soft_cap:
-                kwargs = {"attn_logits_soft_cap": self.logit_soft_cap}
-            else:
-                kwargs = {}
-
             attention_output = ops.dot_product_attention(
                 query,
                 key,
                 value,
                 mask=attention_mask,
                 scale=self._inv_norm_factor,
-                **kwargs,
             )
             return attention_output
 
@@ -249,15 +238,15 @@ class CachedMixtralAttention(keras.layers.Layer):
         config = super().get_config()
         config.update(
             {
-                "num_query_heads": self._num_query_heads,
-                "num_key_value_heads": self._num_key_value_heads,
-                "rope_max_wavelength": self._rope_max_wavelength,
-                "rope_scaling_factor": self._rope_scaling_factor,
+                "num_query_heads": self.num_query_heads,
+                "num_key_value_heads": self.num_key_value_heads,
+                "rope_max_wavelength": self.rope_max_wavelength,
+                "rope_scaling_factor": self.rope_scaling_factor,
                 "kernel_initializer": keras.initializers.serialize(
                     self._kernel_initializer
                 ),
-                "sliding_window": self._sliding_window,
-                "dropout": self._dropout,
+                "sliding_window": self.sliding_window,
+                "dropout": self.dropout,
             }
         )
         return config

keras_hub/src/models/mixtral/mixtral_presets.py

@@ -10,7 +10,7 @@ backbone_presets = {
             "params": 46702792704,
             "path": "mixtral",
         },
-        "kaggle_handle": "kaggle://keras/mixtral/keras/mixtral_8_7b_en",
+        "kaggle_handle": "kaggle://keras/mixtral/keras/mixtral_8_7b_en/3",
     },
     "mixtral_8_instruct_7b_en": {
         "metadata": {
@@ -21,6 +21,6 @@ backbone_presets = {
             "params": 46702792704,
             "path": "mixtral",
         },
-        "kaggle_handle": "kaggle://keras/mixtral/keras/mixtral_8_instruct_7b_en",
+        "kaggle_handle": "kaggle://keras/mixtral/keras/mixtral_8_instruct_7b_en/3",
     },
 }

keras_hub/src/models/moonshine/moonshine_presets.py

@@ -9,7 +9,7 @@ backbone_presets = {
             "params": 27092736,
             "path": "moonshine",
         },
-        "kaggle_handle": "kaggle://keras/moonshine/Keras/moonshine_tiny_en",
+        "kaggle_handle": "kaggle://keras/moonshine/Keras/moonshine_tiny_en/1",
     },
     "moonshine_base_en": {
         "metadata": {
@@ -20,6 +20,6 @@ backbone_presets = {
             "params": 61513920,
             "path": "moonshine",
         },
-        "kaggle_handle": "kaggle://keras/moonshine/Keras/moonshine_base_en",
+        "kaggle_handle": "kaggle://keras/moonshine/Keras/moonshine_base_en/1",
     },
 }

keras_hub/src/models/pali_gemma/pali_gemma_presets.py

@@ -81,7 +81,7 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_ft_docci_10b_448/2",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_ft_docci_10b_448/3",
     },
     "pali_gemma2_mix_3b_224": {
         "metadata": {
@@ -126,7 +126,7 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_mix_10b_224/2",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_mix_10b_224/3",
     },
     "pali_gemma2_mix_10b_448": {
         "metadata": {
@@ -141,7 +141,7 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_mix_10b_448/2",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_mix_10b_448/3",
     },
     "pali_gemma2_mix_28b_224": {
         "metadata": {
@@ -156,7 +156,7 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_28b_mix_224/2",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_28b_mix_224/3",
     },
     "pali_gemma2_mix_28b_448": {
         "metadata": {
@@ -171,7 +171,7 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_28b_mix_448/2",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_28b_mix_448/3",
     },
     "pali_gemma2_pt_3b_224": {
         "metadata": {
@@ -231,7 +231,7 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_10b_224/2",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_10b_224/3",
     },
     "pali_gemma2_pt_10b_448": {
         "metadata": {
@@ -246,7 +246,7 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_10b_448/2",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_10b_448/3",
     },
     "pali_gemma2_pt_10b_896": {
         "metadata": {
@@ -261,7 +261,7 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_10b_896/2",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_10b_896/3",
     },
     "pali_gemma2_pt_28b_224": {
         "metadata": {
@@ -276,7 +276,7 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_28b_224/3",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_28b_224/4",
     },
     "pali_gemma2_pt_28b_448": {
         "metadata": {
@@ -291,7 +291,7 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_28b_448/2",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_28b_448/3",
     },
     "pali_gemma2_pt_28b_896": {
         "metadata": {
@@ -306,6 +306,6 @@ backbone_presets = {
             "path": "pali_gemma2",
             "model_card": "https://www.kaggle.com/models/google/paligemma-2",
         },
-        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_28b_896/2",
+        "kaggle_handle": "kaggle://keras/paligemma2/keras/pali_gemma2_pt_28b_896/3",
     },
 }

keras_hub/src/models/qwen/qwen_presets.py

@@ -7,7 +7,7 @@ backbone_presets = {
             "params": 494032768,
             "path": "qwen",
         },
-        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_0.5b_en",
+        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_0.5b_en/1",
     },
     "qwen2.5_3b_en": {
         "metadata": {
@@ -15,7 +15,7 @@ backbone_presets = {
             "params": 3085938688,
             "path": "qwen",
         },
-        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_3b_en",
+        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_3b_en/1",
     },
     "qwen2.5_7b_en": {
         "metadata": {
@@ -23,7 +23,7 @@ backbone_presets = {
             "params": 6993420288,
             "path": "qwen",
         },
-        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_7b_en/2",
+        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_7b_en/3",
     },
     "qwen2.5_instruct_0.5b_en": {
         "metadata": {
@@ -34,7 +34,7 @@ backbone_presets = {
             "params": 494032768,
             "path": "qwen",
         },
-        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_instruct_0.5b_en",
+        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_instruct_0.5b_en/1",
     },
     "qwen2.5_instruct_32b_en": {
         "metadata": {
@@ -45,7 +45,7 @@ backbone_presets = {
             "params": 32763876352,
             "path": "qwen",
         },
-        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_instruct_32b_en",
+        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_instruct_32b_en/2",
     },
     "qwen2.5_instruct_72b_en": {
         "metadata": {
@@ -56,6 +56,6 @@ backbone_presets = {
             "params": 72706203648,
             "path": "qwen",
         },
-        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_instruct_72b_en",
+        "kaggle_handle": "kaggle://keras/qwen/keras/qwen2.5_instruct_72b_en/2",
     },
 }

keras_hub/src/models/qwen_moe/qwen_moe_attention.py

@@ -256,9 +256,6 @@ class QwenMoeAttention(keras.layers.Layer):
         if self.dropout > 0.0:
             return False
         if running_on_gpu():
-            # GPU never supports softcap in the fused op.
-            if self.logit_soft_cap is not None:
-                return False
             return gpu_supports_fused_attention_op()
         elif running_on_tpu():
             # TPU supports softcap with on keras >= 3.10.
@@ -268,7 +265,13 @@ class QwenMoeAttention(keras.layers.Layer):
             return False
 
     def _compute_attention(
-        self, query, key, value, attention_mask=None, cache_update_index=None
+        self,
+        query,
+        key,
+        value,
+        attention_mask=None,
+        cache_update_index=None,
+        **kwargs,
     ):
         """Computes attention using query, key, and value tensors.
 
@@ -289,11 +292,6 @@ class QwenMoeAttention(keras.layers.Layer):
                 attention_mask = ops.expand_dims(attention_mask, axis=1)
                 attention_mask = ops.cast(attention_mask, dtype="bool")
 
-            if self.logit_soft_cap:
-                kwargs = {"attn_logits_soft_cap": self.logit_soft_cap}
-            else:
-                kwargs = {}
-
             attention_output = ops.dot_product_attention(
                 query,
                 key,

keras_hub/src/models/qwen_moe/qwen_moe_presets.py

@@ -10,6 +10,6 @@ backbone_presets = {
             "params": 14315784192,
             "path": "qwen-1.5-moe",
         },
-        "kaggle_handle": "kaggle://keras/qwen-1.5-moe/Keras/qwen1.5_moe_2.7b_en",
+        "kaggle_handle": "kaggle://keras/qwen-1.5-moe/Keras/qwen1.5_moe_2.7b_en/3",
     },
 }

keras_hub/src/utils/transformers/convert_mixtral.py

@@ -68,7 +68,7 @@ def convert_weights(backbone, loader, transformers_config):
         )
         ## Output
         loader.port_weight(
-            keras_variable=decoder_layer._self_attention_layer._output_dense.kernel,
+            keras_variable=decoder_layer._self_attention_layer.output_dense.kernel,
             hf_weight_key=f"model.layers.{i}.self_attn.o_proj.weight",
             hook_fn=transpose_and_reshape,
         )

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__ = "0.21.0.dev202505200408"
+__version__ = "0.21.0.dev202505230409"
 
 
 @keras_hub_export("keras_hub.version")

{keras_hub_nightly-0.21.0.dev202505200408.dist-info → keras_hub_nightly-0.21.0.dev202505230409.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: keras-hub-nightly
-Version: 0.21.0.dev202505200408
+Version: 0.21.0.dev202505230409
 Summary: Pretrained models for Keras.
 Author-email: Keras team <keras-users@googlegroups.com>
 License-Expression: Apache-2.0

{keras_hub_nightly-0.21.0.dev202505200408.dist-info → keras_hub_nightly-0.21.0.dev202505230409.dist-info}/RECORD

@@ -5,7 +5,7 @@ keras_hub/models/__init__.py,sha256=itSzodVUeuX6HQnmsSXY0Wv-5Htbu397410R-SFW_4I,
 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=16Dlkn6itEVzBVI5lZYq-aU9ij4T2GIfi9kAgEFRhGc,222
+keras_hub/src/version.py,sha256=SjWdrHYDbNitBzSsMmxG-HvuuqsSB3ICvTQclkoX-Os,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
@@ -189,7 +189,7 @@ keras_hub/src/models/gemma/gemma_backbone.py,sha256=GzAUSArw_pN9dtWQzTVhWDbW-XyW
 keras_hub/src/models/gemma/gemma_causal_lm.py,sha256=3OXaIXlrKqMIuUnBk-bUz-0SYFL-XkkQTWm8qRY2YII,16770
 keras_hub/src/models/gemma/gemma_causal_lm_preprocessor.py,sha256=bpKkEurWIfa6Kp9s4pz84-sBDSA6ZFNHP8nXG1fFQrg,2912
 keras_hub/src/models/gemma/gemma_decoder_block.py,sha256=f5UsRO-VNsKJfm_WHVJWK4UahhzYm3sKprJ8jjr-zm4,7628
-keras_hub/src/models/gemma/gemma_presets.py,sha256=lWPjEb_6pFC1vdX7mwxf-C2im93YygmlSPjWvqnLWic,7178
+keras_hub/src/models/gemma/gemma_presets.py,sha256=ZOZEZP3MaIn4-y5i0-QxNeAVtNoWvVYTAu96wvIFMpA,7178
 keras_hub/src/models/gemma/gemma_tokenizer.py,sha256=FhcyNL4lo63MqOhTQPFr07-u3BddL0fVM4TmOm8ku-I,2622
 keras_hub/src/models/gemma/rms_normalization.py,sha256=fku-JEo2sNy-ytX7ySD1sRzdhRAPmYex_z8oFk1NiG8,833
 keras_hub/src/models/gemma3/__init__.py,sha256=oPFadkdK5DRLD6sYx83iTetY5daWuSzmJilLjokHcbU,257
@@ -200,7 +200,7 @@ keras_hub/src/models/gemma3/gemma3_causal_lm_preprocessor.py,sha256=vjt4N-zr0Eb5
 keras_hub/src/models/gemma3/gemma3_decoder_block.py,sha256=6PLlpDxxF67stDv74fw9nNgUHBWmTLx6qGygJwyu5FY,10819
 keras_hub/src/models/gemma3/gemma3_image_converter.py,sha256=czi5JrTyKiK0nFzvonviBIX8jjvLHqvGNA9RyheB31k,536
 keras_hub/src/models/gemma3/gemma3_interleave_embeddings.py,sha256=_Q5hvhA93HAJe-A2IBRKVu0_RDVht61lFQiYse_9Rm4,4597
-keras_hub/src/models/gemma3/gemma3_presets.py,sha256=--V8AV9VLk8GJ9JmyVAfZfSPe_d_p0L60bdyED04ig0,5124
+keras_hub/src/models/gemma3/gemma3_presets.py,sha256=tVxug3rX3w_lqZlFfyqUlVdOrfBjN0GJY5ooBx1Fe0M,5124
 keras_hub/src/models/gemma3/gemma3_tokenizer.py,sha256=ZaBclFIwzJkSXDuZMBQLHUKV8RWEdZ_dsJMvMcc3qXw,3215
 keras_hub/src/models/gemma3/gemma3_vision_encoder.py,sha256=7XI0oBjIfJItV5w90t5bWb3C2KzjhvDnIC7wjIq4Cns,20850
 keras_hub/src/models/gemma3/rms_normalization.py,sha256=fku-JEo2sNy-ytX7ySD1sRzdhRAPmYex_z8oFk1NiG8,833
@@ -225,14 +225,14 @@ keras_hub/src/models/llama/llama_causal_lm.py,sha256=9bP4-XDCMgsZuH1ILIMzmwq2Fyy
 keras_hub/src/models/llama/llama_causal_lm_preprocessor.py,sha256=VTboOMiRBoxHrwP343upLUTsv3AG65r2H8h_PNPVphE,3047
 keras_hub/src/models/llama/llama_decoder.py,sha256=CfWI8ru1-uWjDs0sL6H7g8ElYXWu6h7c5XIx-2Y8lX8,9668
 keras_hub/src/models/llama/llama_layernorm.py,sha256=LfRbePHUJs00Ptf7dvNaw3Aj9n1xBMBpE_rS5zzsYMo,1050
-keras_hub/src/models/llama/llama_presets.py,sha256=k0JPQggSQ0XUkhiPlfM0gTqHXGOt39InVLglPUi4AJU,1902
+keras_hub/src/models/llama/llama_presets.py,sha256=B-WwL4g0Oiml1pyVwQrfIwvjm8jyLlBvwEE-KvkXayU,1902
 keras_hub/src/models/llama/llama_rotary_embedding.py,sha256=nqQGl7lFXJq7xGBfoONx2-wuuvKdoydnzUjy6FGQjwo,7300
 keras_hub/src/models/llama/llama_tokenizer.py,sha256=NKWhxTutQ2jd6sd3NSTy9plQyKGCmuNG7U6kVxhZU4Y,1981
 keras_hub/src/models/llama3/__init__.py,sha256=Vqvr2E10cnANkrRQGNBJtVLNAu-Bg9Lx6sqKOZWFy_8,257
 keras_hub/src/models/llama3/llama3_backbone.py,sha256=TEocD8X7GihQFGJAz3jPwLCqDb86nyeZ1DqBF7RgQLE,3366
 keras_hub/src/models/llama3/llama3_causal_lm.py,sha256=qk_onuf7S6d7rxAntilq2Q2orggMbPEJbNHJNVe2G0U,1541
 keras_hub/src/models/llama3/llama3_causal_lm_preprocessor.py,sha256=twbXel9hsQgGxDAoQhEQuVm2udnEybI4fAQTJzXAuBs,3064
-keras_hub/src/models/llama3/llama3_presets.py,sha256=--_6Uao-fK4xD4ShgsqzKmlyQPyO9tRkF0VDYKjGpNw,4302
+keras_hub/src/models/llama3/llama3_presets.py,sha256=m5WEWOKm58wp7w_SDhYFVv3XhdY6d0GfSwxlbH07rwM,4302
 keras_hub/src/models/llama3/llama3_tokenizer.py,sha256=J-KxRc08vGs4olFw_4mtJs0W_dTeUyj_XxMycazBmxI,1934
 keras_hub/src/models/mistral/__init__.py,sha256=vjBlzcrIsFSwJKnfwfTNMKstIEKGFTE3kVcdAdfwlnE,263
 keras_hub/src/models/mistral/mistral_attention.py,sha256=nGDlD4NcIwIGlfbt3ArxdT5QAvamY7yiNEGDlTgWirU,8609
@@ -240,7 +240,7 @@ keras_hub/src/models/mistral/mistral_backbone.py,sha256=oatoqSX0z-xjKfXeSveL4P0D
 keras_hub/src/models/mistral/mistral_causal_lm.py,sha256=ujCKfsbuYzr8VusqPYcnTH6rTb0MRfzsinEraVhQksc,13234
 keras_hub/src/models/mistral/mistral_causal_lm_preprocessor.py,sha256=_4qq-uKktfIg_i081ZWjZGEIYZpedBwtBGpchQQ-qEk,3079
 keras_hub/src/models/mistral/mistral_layer_norm.py,sha256=nimMZ5CTPK8v9eflfrGuzqmv-2vd2rGlPvcHOMwYZyg,1063
-keras_hub/src/models/mistral/mistral_presets.py,sha256=76Cctnl-UXFtl76OFzMl7Q0E-oJuizbpIHoDlYA1pBI,939
+keras_hub/src/models/mistral/mistral_presets.py,sha256=ggWQwKGDMFPzUWkQIJ6Tlk7NS-dClRO95WoSTaImL9s,939
 keras_hub/src/models/mistral/mistral_tokenizer.py,sha256=wyzR_Y2XwrDiBV3jIeBChSPiaOkVVaxFuLxMH2F6EYA,2005
 keras_hub/src/models/mistral/mistral_transformer_decoder.py,sha256=z5FCh9TEaznvhW3JOSKmFTotRbiuQhzJTZClW2m9sEw,9556
 keras_hub/src/models/mit/__init__.py,sha256=F70_0PR_nPzPdMI8XOpXDRR_nxclGjcHv3iWSWUX3w8,316
@@ -250,13 +250,13 @@ keras_hub/src/models/mit/mit_image_classifier_preprocessor.py,sha256=oNYs-pUK8Vn
 keras_hub/src/models/mit/mit_image_converter.py,sha256=Mw7nV-OzyBveGuZUNFsPPKyq9jXJVW2_cVH024CNkXM,311
 keras_hub/src/models/mit/mit_layers.py,sha256=HUJO5uhJ6jgwANpwbQdPlEVwLRVb3BZQ-Ftjg3B9XvY,9734
 keras_hub/src/models/mit/mit_presets.py,sha256=ooLrh2OoGZKxnCGnhB6BynYJtVCXH7nDDFhgQRWt36U,4528
-keras_hub/src/models/mixtral/mixtral_attention.py,sha256=rdUBjIFQZKBpyCXlXMDgmB8gLCk0ngnhdhNs_twFE_c,9089
+keras_hub/src/models/mixtral/mixtral_attention.py,sha256=f5aiTtstWeKG_ZwumAlYIzjIN08CpnxNdenxWNJSwZw,8713
 keras_hub/src/models/mixtral/mixtral_backbone.py,sha256=vUAFXvqwVBgKxYbOsqIHzPN59bhaDrGWwOnBCzeUtt0,8034
 keras_hub/src/models/mixtral/mixtral_causal_lm.py,sha256=JA1t6xTeaYX_fNo9ftRyvzdRDG3vndC-Rlwn5fnsbQo,12001
 keras_hub/src/models/mixtral/mixtral_causal_lm_preprocessor.py,sha256=q2qXa9QAUWBvOWv9DeNvwsBNXSORJAbQFoQsWQ7e8V8,3079
 keras_hub/src/models/mixtral/mixtral_decoder.py,sha256=CvOjhTxPnGQ_HNknZXRI6Cx1kpuHG99_TiOh-mNcsDw,18190
 keras_hub/src/models/mixtral/mixtral_layer_norm.py,sha256=zfbDKZEb45FTwP0zQd7WPPp8tuiGoSNfS-DRYWkZyWw,1031
-keras_hub/src/models/mixtral/mixtral_presets.py,sha256=XRwOkSDzZ8h42Onhf9AYh3DS_IxAQGICISiPLW_e5po,852
+keras_hub/src/models/mixtral/mixtral_presets.py,sha256=AteLrYXyVjooz_DHLnBA1OMlZS6LMu7Y7gGUWddn6go,856
 keras_hub/src/models/mixtral/mixtral_tokenizer.py,sha256=Kc233k879QMyX164X_CzWbqpnqEkKWNqa648guTGkBk,661
 keras_hub/src/models/mobilenet/__init__.py,sha256=hxkNGGj_iAMu62iooUDEPA818sNOIgjG7pXMLEMOsAE,275
 keras_hub/src/models/mobilenet/mobilenet_backbone.py,sha256=aZBSFeLUObYYoi3od9DI1KfgPCqh5GHTcAI8Y2ZHShA,29536
@@ -274,7 +274,7 @@ keras_hub/src/models/moonshine/moonshine_decoder.py,sha256=Exf5Gg1gsCBST53wxOgBe
 keras_hub/src/models/moonshine/moonshine_encoder.py,sha256=NjjMO_FEBlWFSv6Appv8a3V7XovW2afvxxjXwQRgV60,8148
 keras_hub/src/models/moonshine/moonshine_layers.py,sha256=EIiIMz-UK1nikrC7iusGqjb3jcvmu6VdNcnhWAQHs_M,9538
 keras_hub/src/models/moonshine/moonshine_multi_head_attention.py,sha256=YaxWxdywUyOQDW-KSX9DqXkX0ttGL-p1hRtWuAnlMaE,13598
-keras_hub/src/models/moonshine/moonshine_presets.py,sha256=p0_U8K86RDZlrW2Sd4O_7KFespgZ-Da1raDf9PUXXMw,872
+keras_hub/src/models/moonshine/moonshine_presets.py,sha256=oqawiALSEwZVUhGejyprF4r1009k8930bz3EWJ6YpU8,876
 keras_hub/src/models/moonshine/moonshine_tokenizer.py,sha256=grD-x4hMZDJYEyxvCyV-FYvUFInYsUI08-vnBKLAl5Y,2215
 keras_hub/src/models/opt/__init__.py,sha256=6Ybj8etxNaPsVcuZvaeHnKB3As92Px--dbiFAqOCIT0,239
 keras_hub/src/models/opt/opt_backbone.py,sha256=mK5z_E5mSiIX5s0w4hr4IVQpT7K46W2ajZBmuMjxwaY,5873
@@ -288,7 +288,7 @@ keras_hub/src/models/pali_gemma/pali_gemma_causal_lm.py,sha256=AViEs6YltUqWnIVo7
 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
-keras_hub/src/models/pali_gemma/pali_gemma_presets.py,sha256=zF04iShXky_c3IfUbmLlBN2FYb6iCWH1DWTgDdTCqrI,13006
+keras_hub/src/models/pali_gemma/pali_gemma_presets.py,sha256=DAaSzquR4_AnSjToDjgXj2zbrT5skUpXmzKoyATwwHk,13006
 keras_hub/src/models/pali_gemma/pali_gemma_tokenizer.py,sha256=ljTiADHo0Ok88q-jVzwJIle2C8xcxnudLTsBLzIySaM,2415
 keras_hub/src/models/pali_gemma/pali_gemma_vit.py,sha256=SbWanwCoONSwgiWQsc6lFdvhqKZ-zDW42XzQt8CNMtU,18311
 keras_hub/src/models/phi3/__init__.py,sha256=zIbf1MU-ks91mEkjTRJAsk51N3BBnXDF2JM1vO-13PQ,245
@@ -308,16 +308,16 @@ keras_hub/src/models/qwen/qwen_causal_lm.py,sha256=_f-UHaKHp0ncxknpkpEJiW3jlng3E
 keras_hub/src/models/qwen/qwen_causal_lm_preprocessor.py,sha256=Va-4TLJD3ycEnkS41rF3dVj4_6K0j-gxLTrREFRcyr0,609
 keras_hub/src/models/qwen/qwen_decoder.py,sha256=utmAvZlU7_nP-6pjGPDinK4JaMzsQSwOARG0ote-jAg,11771
 keras_hub/src/models/qwen/qwen_layernorm.py,sha256=DS35r3qd6g5ocL7Nhf_vNzLLMo1aI9VCSmL64dgNOYI,924
-keras_hub/src/models/qwen/qwen_presets.py,sha256=_jRG7bB4yBGWteBLbK2elc1e9doRl8zdzQRZgxFvnfc,1988
+keras_hub/src/models/qwen/qwen_presets.py,sha256=DpRplWNwktM4KDgIP495PTUBJxQE_mS6KQSK5LGWOyc,1998
 keras_hub/src/models/qwen/qwen_tokenizer.py,sha256=LCv3IyiDDHqVnM9N3lf5-BE3iwicIh0nKS1hjoPw9lE,1532
 keras_hub/src/models/qwen_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-keras_hub/src/models/qwen_moe/qwen_moe_attention.py,sha256=mXc4uGkUSK3FHdJ5_77xiX7Gm0eO1GWTF40ei_68pvU,13472
+keras_hub/src/models/qwen_moe/qwen_moe_attention.py,sha256=pE79_iHUm2LGkoWL6zMJw_pNfzIvmyq3yJaiq47W2TY,13242
 keras_hub/src/models/qwen_moe/qwen_moe_backbone.py,sha256=nrfELvIvRLmrgKrUNXci2CrecmeI6bWzJj7HH-RcWJA,15341
 keras_hub/src/models/qwen_moe/qwen_moe_causal_lm.py,sha256=MeP60v7GcN_SmH5_ULRpqgmFVgaYAosSecZiSQVlJvU,13256
 keras_hub/src/models/qwen_moe/qwen_moe_causal_lm_preprocessor.py,sha256=uKaXRrJs02vkVudjdehzJPp0B84tPMkxNHlp166kceE,589
 keras_hub/src/models/qwen_moe/qwen_moe_decoder.py,sha256=kmUjLpYTbJQ3J_31qWhLOd0Dg2_9cl_JX_zM8ZMH1Qo,23130
 keras_hub/src/models/qwen_moe/qwen_moe_layernorm.py,sha256=DbkWJo7U0-cwdZwHPeAnFznYwtao6o0fjpoDJ9UWnpc,927
-keras_hub/src/models/qwen_moe/qwen_moe_presets.py,sha256=gzNtpVValNi1tjHWa-OHw6BChys9cEJk98aP56zyyUg,455
+keras_hub/src/models/qwen_moe/qwen_moe_presets.py,sha256=uKrA9xLV3P3jtYUUsqdhKq_HPkB4lXmOYseB1wXTZnI,457
 keras_hub/src/models/qwen_moe/qwen_moe_tokenizer.py,sha256=2c3X8jNGO0q0UL5NtUqSgHWLqhyJGi2ohNcTeOGhd84,1407
 keras_hub/src/models/resnet/__init__.py,sha256=C5UqlQ6apm8WSp1bnrxB6Bi3BGaknxRQs-r3b2wpaGA,257
 keras_hub/src/models/resnet/resnet_backbone.py,sha256=Q7nlqcTXZzjqd0e-DsjHC4ok58yOX7qxseotym3uZpM,31276
@@ -490,7 +490,7 @@ keras_hub/src/utils/transformers/convert_gemma.py,sha256=ElCgwBpSN5Q7rV5PJawTsoy
 keras_hub/src/utils/transformers/convert_gpt2.py,sha256=HCeHN_-GiQJRxLCM9OCJJ1watPVpIBF8ujS8pGbBOWc,5703
 keras_hub/src/utils/transformers/convert_llama3.py,sha256=c5phNl-QayQ_BS0s-lenbu6oHxqfwDShKJoh9DluxUU,6146
 keras_hub/src/utils/transformers/convert_mistral.py,sha256=kVhN9h1ZFVhwkNW8p3wnS7eANJUXIsNy1RxWXy20Gqw,4760
-keras_hub/src/utils/transformers/convert_mixtral.py,sha256=_esUzVRYABR5pHHSALqUieSuAeBg4te1JnlGQENqECU,5509
+keras_hub/src/utils/transformers/convert_mixtral.py,sha256=PxeCY8Xe7U_caICugwOCEjuSZ51ZUtmef6rUxh-Wt54,5508
 keras_hub/src/utils/transformers/convert_pali_gemma.py,sha256=B1leeDw96Yvu81hYumf66hIid07k5NLqoeWAJgPnaLs,10649
 keras_hub/src/utils/transformers/convert_qwen.py,sha256=WUxMAEFVqRs7TRw7QU5TH3_ev4yf02R1xFVliMvTQqg,5886
 keras_hub/src/utils/transformers/convert_qwen_moe.py,sha256=a7R28aln-PdAcNuKAXdrtzvslho2Co6GypChxLMKPpc,10618
@@ -499,7 +499,7 @@ keras_hub/src/utils/transformers/preset_loader.py,sha256=1nfS5xVsl-JROGXJXltTqV1
 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-0.21.0.dev202505200408.dist-info/METADATA,sha256=1G-1i8uPTWmHiGqhTz4-2JahMqvxpwNCAe-hTtq5foo,7393
-keras_hub_nightly-0.21.0.dev202505200408.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
-keras_hub_nightly-0.21.0.dev202505200408.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
-keras_hub_nightly-0.21.0.dev202505200408.dist-info/RECORD,,
+keras_hub_nightly-0.21.0.dev202505230409.dist-info/METADATA,sha256=i-P2LqVLiVN0cIr63OvwxpAmqn2sGBPSUHDqbHiFhcg,7393
+keras_hub_nightly-0.21.0.dev202505230409.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
+keras_hub_nightly-0.21.0.dev202505230409.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
+keras_hub_nightly-0.21.0.dev202505230409.dist-info/RECORD,,

{keras_hub_nightly-0.21.0.dev202505200408.dist-info → keras_hub_nightly-0.21.0.dev202505230409.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.7.1)
+Generator: setuptools (80.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any