Upload folder using huggingface_hub

README.md

@@ -0,0 +1,12 @@
+---
+library_name: keras-hub
+---
+This is a [`CLIP` model](https://keras.io/api/keras_hub/models/clip) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
+Model config:
+* **name:** clip_backbone
+* **trainable:** True
+* **vision_encoder:** {'module': 'keras_hub.src.models.clip.clip_vision_encoder', 'class_name': 'CLIPVisionEncoder', 'config': {'name': 'clip_vision_encoder', 'trainable': True, 'patch_size': 14, 'hidden_dim': 1024, 'num_layers': 24, 'num_heads': 16, 'intermediate_dim': 4096, 'intermediate_activation': 'quick_gelu', 'intermediate_output_index': None, 'image_shape': [336, 336, 3]}, 'registered_name': 'keras_hub>CLIPVisionEncoder'}
+* **text_encoder:** {'module': 'keras_hub.src.models.clip.clip_text_encoder', 'class_name': 'CLIPTextEncoder', 'config': {'name': 'clip_text_encoder', 'trainable': True, 'vocabulary_size': 49408, 'embedding_dim': 768, 'hidden_dim': 768, 'num_layers': 12, 'num_heads': 12, 'intermediate_dim': 3072, 'intermediate_activation': 'quick_gelu', 'intermediate_output_index': None, 'max_sequence_length': 77}, 'registered_name': 'keras_hub>CLIPTextEncoder'}
+* **projection_dim:** 768
+
+This model card has been generated automatically and should be completed by the model author. See [Model Cards documentation](https://huggingface.co/docs/hub/model-cards) for more information.

config.json

@@ -0,0 +1,49 @@
+{
+    "module": "keras_hub.src.models.clip.clip_backbone",
+    "class_name": "CLIPBackbone",
+    "config": {
+        "name": "clip_backbone",
+        "trainable": true,
+        "vision_encoder": {
+            "module": "keras_hub.src.models.clip.clip_vision_encoder",
+            "class_name": "CLIPVisionEncoder",
+            "config": {
+                "name": "clip_vision_encoder",
+                "trainable": true,
+                "patch_size": 14,
+                "hidden_dim": 1024,
+                "num_layers": 24,
+                "num_heads": 16,
+                "intermediate_dim": 4096,
+                "intermediate_activation": "quick_gelu",
+                "intermediate_output_index": null,
+                "image_shape": [
+                    336,
+                    336,
+                    3
+                ]
+            },
+            "registered_name": "keras_hub>CLIPVisionEncoder"
+        },
+        "text_encoder": {
+            "module": "keras_hub.src.models.clip.clip_text_encoder",
+            "class_name": "CLIPTextEncoder",
+            "config": {
+                "name": "clip_text_encoder",
+                "trainable": true,
+                "vocabulary_size": 49408,
+                "embedding_dim": 768,
+                "hidden_dim": 768,
+                "num_layers": 12,
+                "num_heads": 12,
+                "intermediate_dim": 3072,
+                "intermediate_activation": "quick_gelu",
+                "intermediate_output_index": null,
+                "max_sequence_length": 77
+            },
+            "registered_name": "keras_hub>CLIPTextEncoder"
+        },
+        "projection_dim": 768
+    },
+    "registered_name": "keras_hub>CLIPBackbone"
+}

image_converter.json

@@ -0,0 +1,33 @@
+{
+    "module": "keras_hub.src.models.clip.clip_image_converter",
+    "class_name": "CLIPImageConverter",
+    "config": {
+        "name": "clip_image_converter",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "float32"
+            },
+            "registered_name": null
+        },
+        "image_size": [
+            336,
+            336
+        ],
+        "scale": [
+            0.014598426619242919,
+            0.015007768493717055,
+            0.014220065717024086
+        ],
+        "offset": [
+            -1.79226253374815,
+            -1.7520971281645974,
+            -1.4802197687835659
+        ],
+        "interpolation": "bicubic",
+        "crop_to_aspect_ratio": true
+    },
+    "registered_name": "keras_hub>CLIPImageConverter"
+}

metadata.json

@@ -0,0 +1,6 @@
+{
+    "keras_version": "3.6.0",
+    "keras_hub_version": "0.17.0.dev0",
+    "parameter_count": 427944770,
+    "date_saved": "2024-10-29@23:00:18"
+}

model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e1ed23e32e204f2019c5c9af6fe03a6d90b048232cc3b4f4430b8bb00ce7bb
+size 1712969228

tokenizer.json

@@ -0,0 +1,21 @@
+{
+    "module": "keras_hub.src.models.clip.clip_tokenizer",
+    "class_name": "CLIPTokenizer",
+    "config": {
+        "name": "clip_tokenizer",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "int32"
+            },
+            "registered_name": null
+        },
+        "config_file": "tokenizer.json",
+        "sequence_length": null,
+        "add_prefix_space": false,
+        "pad_with_end_token": true
+    },
+    "registered_name": "keras_hub>CLIPTokenizer"
+}