upload model

README.md

@@ -1,3 +1,5 @@
 ---
 license: cc-by-nc-4.0
+tags:
+  - transformers.js
 ---

config.json

@@ -0,0 +1,20 @@
+{
+  "_name_or_path": "facebook/metaclip-b16-fullcc2.5b",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 512,
+  "text_config": {
+    "heads": 8,
+    "layers": 12,
+    "model_type": "clip_text_model"
+  },
+  "transformers_version": "4.45.2",
+  "vision_config": {
+    "model_type": "clip_vision_model",
+    "patch_size": 16
+  }
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63fb5d5fadf18379e86ec8073044200b40d336668d206323c5eaaed612cef52b
+size 599135855

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe60cd9f449585416b090b57aee967cfd5a59bab59b9c342b6458f06af266e3
+size 151988869

onnx/text_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350b52b451e87421331d19a24ed3cbe6c4b21b11a0934d623b7f9b8a8c47a017
+size 254059280

onnx/text_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af182f98259dd7418b3d88ac85ed473fb0b9df5675a941b602ba0faaae4df243
+size 64529343

onnx/vision_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962f4e8a124bb72311172478ac9a6bca90e92c046ad2f67b03184cc9ea8d849d
+size 345075087

onnx/vision_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342e70c0f41ef40e45063c38c0e812a48ab29d88db73191c220f0eac28017efd
+size 87500784

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPFeatureExtractor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

quantize_config.json

@@ -0,0 +1,104 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "vision_model": {
+            "op_types": [
+                "Add",
+                "Slice",
+                "Sub",
+                "Where",
+                "Shape",
+                "Reshape",
+                "MatMul",
+                "ConstantOfShape",
+                "Concat",
+                "Sqrt",
+                "Pow",
+                "Gather",
+                "Softmax",
+                "Div",
+                "Constant",
+                "Equal",
+                "Conv",
+                "Expand",
+                "Unsqueeze",
+                "Mul",
+                "Transpose",
+                "Cast",
+                "Sigmoid",
+                "ReduceMean"
+            ],
+            "weight_type": "QUInt8"
+        },
+        "text_model": {
+            "op_types": [
+                "Add",
+                "Slice",
+                "ArgMax",
+                "Sub",
+                "Where",
+                "Shape",
+                "Squeeze",
+                "Reshape",
+                "Less",
+                "MatMul",
+                "ConstantOfShape",
+                "Concat",
+                "Sqrt",
+                "Range",
+                "Pow",
+                "Gather",
+                "Softmax",
+                "Flatten",
+                "Div",
+                "Constant",
+                "Equal",
+                "Expand",
+                "Unsqueeze",
+                "Mul",
+                "Transpose",
+                "Cast",
+                "Sigmoid",
+                "ReduceMean"
+            ],
+            "weight_type": "QInt8"
+        },
+        "model": {
+            "op_types": [
+                "Add",
+                "Slice",
+                "ArgMax",
+                "Sub",
+                "Where",
+                "Shape",
+                "Squeeze",
+                "Reshape",
+                "Less",
+                "MatMul",
+                "ConstantOfShape",
+                "Concat",
+                "Sqrt",
+                "Range",
+                "Pow",
+                "Gather",
+                "Exp",
+                "Softmax",
+                "Flatten",
+                "Div",
+                "ReduceSum",
+                "Constant",
+                "Equal",
+                "Conv",
+                "Expand",
+                "Unsqueeze",
+                "Mul",
+                "Transpose",
+                "Cast",
+                "Sigmoid",
+                "ReduceMean"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}