Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+library_name: transformers.js
+base_model:
+- google/owlv2-large-patch14
+---
+
+# owlv2-large-patch14 (ONNX)
+
+This is an ONNX version of [google/owlv2-large-patch14](https://huggingface.co/google/owlv2-large-patch14). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).

config.json

@@ -0,0 +1,30 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "google/owlv2-large-patch14",
+  "architectures": [
+    "Owlv2ForObjectDetection"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "owlv2",
+  "projection_dim": 768,
+  "text_config": {
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "owlv2_text_model",
+    "num_attention_heads": 12,
+    "torch_dtype": "float32"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 1008,
+    "intermediate_size": 4096,
+    "model_type": "owlv2_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "torch_dtype": "float32"
+  }
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e53902be0a8761d263bae351e899ba8c45b0e2bd49f17722261ff43127c44c
+size 1739806508

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed799ad336be1d94d0c63f412c71bfd7f86a814da80cf6d972e1b94ee0529579
+size 397827320

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:675a04fa399d6e00a1059349e410590e213c766280092ee4da8117ffa7bfa8d3
+size 870317341

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b376053cc026b0cf85c5712cfe05d2e3176d9eae04cb8dc5f615a39aa283e2e
+size 453224793

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d578f545bbb3c0299a695361a942ec4a19b31a840ccbd658ce1e0173c15c4a4b
+size 422225823

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da93fd07b96a2009a99f29f2c808f4cb5aca5b3e098fd21f5e972a4ce7daaff
+size 309144690

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53569efe9dc3defb9dc2b4f0f4077955126ec982a55a414ead412c646e05be40
+size 453224902

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53569efe9dc3defb9dc2b4f0f4077955126ec982a55a414ead412c646e05be40
+size 453224902

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Owlv2ImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "Owlv2Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 1008,
+    "width": 1008
+  }
+}

quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": false,
+    "reduce_range": false,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

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": "!",
+    "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 +1,41 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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",
+  "extra_special_tokens": {},
+  "model_max_length": 16,
+  "pad_token": "!",
+  "processor_class": "Owlv2Processor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}