Initial Commit

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,3 @@
+https://huggingface.co/google/siglip-base-patch16-256-multilingual with ONNX weights to be compatible with Transformers.js.
+
+See https://huggingface.co/Xenova/siglip-base-patch16-256

config.json

@@ -0,0 +1,17 @@
+{
+  "_name_or_path": "google/siglip-base-patch16-256-multilingual",
+  "architectures": [
+    "SiglipModel"
+  ],
+  "initializer_factor": 1.0,
+  "model_type": "siglip",
+  "text_config": {
+    "model_type": "siglip_text_model",
+    "vocab_size": 250000
+  },
+  "transformers_version": "4.40.0.dev0",
+  "vision_config": {
+    "image_size": 256,
+    "model_type": "siglip_vision_model"
+  }
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a6029865be6c281a9ea986a83b8f1575ed3d513e423e8dc159bb171b5f3412
+size 1483034127

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c5456b0441dd630db9111e0a9f57efd0204583205b00dbb710303e20382d7c
+size 378447692

onnx/text_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd9cdc7038468810ae7c3bcf79f4d91927e513a5f217f1c2566862ed2558110
+size 1111028169

onnx/text_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbcd59207739cc2a222a881b766d32f37a7297e981f5f9594d36d52b741b0164
+size 278899605

onnx/vision_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe14f53c63107e6363006bbae3f6038d15d6d4a7ce233347fc0382ef09230ba
+size 372004690

onnx/vision_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd7c669514965a47cd1013c8069f2cb144b3e45786c0cf5ec363f283780bc7c
+size 99546268

preprocessor_config.json

@@ -0,0 +1,37 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 256,
+    "width": 256
+  }
+}

quantize_config.json

@@ -0,0 +1,62 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "text_model": {
+            "op_types": [
+                "Gemm",
+                "Tanh",
+                "Div",
+                "Sub",
+                "ReduceMean",
+                "Transpose",
+                "Slice",
+                "Sqrt",
+                "MatMul",
+                "Gather",
+                "Mul",
+                "Reshape",
+                "Cast",
+                "Pow",
+                "Concat",
+                "Softmax",
+                "Constant",
+                "Unsqueeze",
+                "Add",
+                "Shape"
+            ],
+            "weight_type": "QInt8"
+        },
+        "vision_model": {
+            "op_types": [
+                "Gemm",
+                "Tanh",
+                "ConstantOfShape",
+                "Mod",
+                "Div",
+                "Sub",
+                "Transpose",
+                "ReduceMean",
+                "Conv",
+                "Slice",
+                "Sqrt",
+                "MatMul",
+                "Expand",
+                "Gather",
+                "Mul",
+                "Reshape",
+                "Cast",
+                "Pow",
+                "Squeeze",
+                "Concat",
+                "Tile",
+                "Softmax",
+                "Constant",
+                "Unsqueeze",
+                "Add",
+                "Shape"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d188aadabecdaec164a39e0d2307204a0ac9878093d17595dd3351fa0e42ca6
+size 16354761

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "added_tokens_decoder": {
+    "1": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "model_input_names": [
+    "input_ids"
+  ],
+  "model_max_length": 64,
+  "pad_token": "</s>",
+  "processor_class": "SiglipProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SiglipTokenizer",
+  "unk_token": "<unk>"
+}