keras-hub-nightly 0.21.0.dev202505190412__py3-none-any.whl → 0.21.0.dev202505200408__py3-none-any.whl

keras_hub/src/models/mixtral/mixtral_presets.py

@@ -0,0 +1,26 @@
+"""Mixtral preset configurations."""
+
+backbone_presets = {
+    "mixtral_8_7b_en": {
+        "metadata": {
+            "description": (
+                "32-layer Mixtral MoE model with 7 billion",
+                "active parameters and 8 experts per MoE layer.",
+            ),
+            "params": 46702792704,
+            "path": "mixtral",
+        },
+        "kaggle_handle": "kaggle://keras/mixtral/keras/mixtral_8_7b_en",
+    },
+    "mixtral_8_instruct_7b_en": {
+        "metadata": {
+            "description": (
+                "Instruction fine-tuned 32-layer Mixtral MoE model",
+                "with 7 billion active parameters and 8 experts per MoE layer.",
+            ),
+            "params": 46702792704,
+            "path": "mixtral",
+        },
+        "kaggle_handle": "kaggle://keras/mixtral/keras/mixtral_8_instruct_7b_en",
+    },
+}

keras_hub/src/models/qwen_moe/qwen_moe_presets.py

@@ -0,0 +1,15 @@
+"""Qwen MoE preset configurations."""
+
+backbone_presets = {
+    "qwen1.5_moe_2.7b_en": {
+        "metadata": {
+            "description": (
+                "24-layer Qwen MoE model with 2.7 billion active parameters ",
+                "and 8 experts per MoE layer.",
+            ),
+            "params": 14315784192,
+            "path": "qwen-1.5-moe",
+        },
+        "kaggle_handle": "kaggle://keras/qwen-1.5-moe/Keras/qwen1.5_moe_2.7b_en",
+    },
+}

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.dev202505190412"
+__version__ = "0.21.0.dev202505200408"
 
 
 @keras_hub_export("keras_hub.version")

{keras_hub_nightly-0.21.0.dev202505190412.dist-info → keras_hub_nightly-0.21.0.dev202505200408.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: keras-hub-nightly
-Version: 0.21.0.dev202505190412
+Version: 0.21.0.dev202505200408
 Summary: Pretrained models for Keras.
 Author-email: Keras team <keras-users@googlegroups.com>
 License-Expression: Apache-2.0

{keras_hub_nightly-0.21.0.dev202505190412.dist-info → keras_hub_nightly-0.21.0.dev202505200408.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=Ex9dxl2w35Pvy5lOO4q5rzwKWs-azMhBDOmj0KLqisA,222
+keras_hub/src/version.py,sha256=16Dlkn6itEVzBVI5lZYq-aU9ij4T2GIfi9kAgEFRhGc,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
@@ -256,6 +256,7 @@ keras_hub/src/models/mixtral/mixtral_causal_lm.py,sha256=JA1t6xTeaYX_fNo9ftRyvzd
 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_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
@@ -316,6 +317,7 @@ keras_hub/src/models/qwen_moe/qwen_moe_causal_lm.py,sha256=MeP60v7GcN_SmH5_ULRpq
 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_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
@@ -497,7 +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.dev202505190412.dist-info/METADATA,sha256=HT5d5wkdvaNOmzPHL0k1c_WsZVGdwS-tWJ9xIWN3IaU,7393
-keras_hub_nightly-0.21.0.dev202505190412.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
-keras_hub_nightly-0.21.0.dev202505190412.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
-keras_hub_nightly-0.21.0.dev202505190412.dist-info/RECORD,,
+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,,