Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/tokenizer/vocabulary.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,11 @@
+---
+library_name: keras-hub
+---
+This is a [`SigLIP` model](https://keras.io/api/keras_hub/models/sig_lip) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
+Model config:
+* **name:** sig_lip_backbone
+* **trainable:** True
+* **vision_encoder:** {'module': 'keras_hub.src.models.siglip.siglip_vision_encoder', 'class_name': 'SigLIPVisionEncoder', 'config': {'name': 'sig_lip_vision_encoder', 'trainable': True, 'patch_size': 16, 'hidden_dim': 1024, 'num_layers': 24, 'num_heads': 16, 'intermediate_dim': 4096, 'intermediate_activation': 'gelu_approximate', 'layer_norm_epsilon': 1e-06, 'image_shape': [384, 384, 3]}, 'registered_name': 'keras_hub>SigLIPVisionEncoder'}
+* **text_encoder:** {'module': 'keras_hub.src.models.siglip.siglip_text_encoder', 'class_name': 'SigLIPTextEncoder', 'config': {'name': 'sig_lip_text_encoder', 'trainable': True, 'vocabulary_size': 32000, 'embedding_dim': 1024, 'hidden_dim': 1024, 'num_layers': 24, 'num_heads': 16, 'intermediate_dim': 4096, 'intermediate_activation': 'gelu_approximate', 'layer_norm_epsilon': 1e-06, 'max_sequence_length': 64}, 'registered_name': 'keras_hub>SigLIPTextEncoder'}
+
+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.

assets/tokenizer/vocabulary.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5036bed065526c3c212dfbe288752391797c4bb1a284aa18c9a0b23fcaf8ec
+size 798330

config.json

@@ -0,0 +1,48 @@
+{
+    "module": "keras_hub.src.models.siglip.siglip_backbone",
+    "class_name": "SigLIPBackbone",
+    "config": {
+        "name": "sig_lip_backbone",
+        "trainable": true,
+        "vision_encoder": {
+            "module": "keras_hub.src.models.siglip.siglip_vision_encoder",
+            "class_name": "SigLIPVisionEncoder",
+            "config": {
+                "name": "sig_lip_vision_encoder",
+                "trainable": true,
+                "patch_size": 16,
+                "hidden_dim": 1024,
+                "num_layers": 24,
+                "num_heads": 16,
+                "intermediate_dim": 4096,
+                "intermediate_activation": "gelu_approximate",
+                "layer_norm_epsilon": 1e-06,
+                "image_shape": [
+                    384,
+                    384,
+                    3
+                ]
+            },
+            "registered_name": "keras_hub>SigLIPVisionEncoder"
+        },
+        "text_encoder": {
+            "module": "keras_hub.src.models.siglip.siglip_text_encoder",
+            "class_name": "SigLIPTextEncoder",
+            "config": {
+                "name": "sig_lip_text_encoder",
+                "trainable": true,
+                "vocabulary_size": 32000,
+                "embedding_dim": 1024,
+                "hidden_dim": 1024,
+                "num_layers": 24,
+                "num_heads": 16,
+                "intermediate_dim": 4096,
+                "intermediate_activation": "gelu_approximate",
+                "layer_norm_epsilon": 1e-06,
+                "max_sequence_length": 64
+            },
+            "registered_name": "keras_hub>SigLIPTextEncoder"
+        }
+    },
+    "registered_name": "keras_hub>SigLIPBackbone"
+}

image_converter.json

@@ -0,0 +1,36 @@
+{
+    "module": "keras_hub.src.models.siglip.siglip_image_converter",
+    "class_name": "SigLIPImageConverter",
+    "config": {
+        "name": "sig_lip_image_converter",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "float32"
+            },
+            "registered_name": null
+        },
+        "image_size": [
+            384,
+            384
+        ],
+        "scale": [
+            0.00784313725490196,
+            0.00784313725490196,
+            0.00784313725490196
+        ],
+        "offset": [
+            -1.0,
+            -1.0,
+            -1.0
+        ],
+        "interpolation": "bicubic",
+        "antialias": true,
+        "crop_to_aspect_ratio": false,
+        "pad_to_aspect_ratio": false,
+        "bounding_box_format": "yxyx"
+    },
+    "registered_name": "keras_hub>SigLIPImageConverter"
+}

metadata.json

@@ -0,0 +1,7 @@
+{
+    "keras_version": "3.8.0",
+    "keras_hub_version": "0.19.0",
+    "parameter_count": 652479106,
+    "date_saved": "2025-03-01@12:11:53",
+    "tasks": []
+}

model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d22fc2b7123b2eea356fbf9e43460a613b598593c75b99ab09f2f993954f3c1
+size 2611500208

tokenizer.json

@@ -0,0 +1,22 @@
+{
+    "module": "keras_hub.src.models.siglip.siglip_tokenizer",
+    "class_name": "SigLIPTokenizer",
+    "config": {
+        "name": "sig_lip_tokenizer",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "int32"
+            },
+            "registered_name": null
+        },
+        "config_file": "tokenizer.json",
+        "proto": null,
+        "sequence_length": null,
+        "add_bos": false,
+        "add_eos": true
+    },
+    "registered_name": "keras_hub>SigLIPTokenizer"
+}