Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+onnx/image_encoder.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/text_encoder.onnx.data filter=lfs diff=lfs merge=lfs -text

onnx/audio_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d1a6df41b8696e43fc58845880ed2244aaee57e03cab4d236ca6bcdb99d8f06
+size 32886892

onnx/config.json

@@ -0,0 +1,33 @@
+{
+  "model_type": "multi-modal-embed-small",
+  "embedding_dim": 384,
+  "matryoshka_dims": [
+    384,
+    256,
+    128,
+    64,
+    32
+  ],
+  "text_encoder": {
+    "file": "text_encoder.onnx",
+    "input_names": [
+      "input_ids",
+      "attention_mask"
+    ],
+    "max_seq_len": 512
+  },
+  "image_encoder": {
+    "file": "image_encoder.onnx",
+    "input_names": [
+      "pixel_values"
+    ],
+    "image_size": 512
+  },
+  "audio_encoder": {
+    "file": "audio_encoder.onnx",
+    "input_names": [
+      "mel_spectrogram"
+    ],
+    "n_mels": 80
+  }
+}

onnx/image_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e2adca1096b19596a2538a2edc577ad1ec76ab4e1311fbf8574b8b51bf78f4
+size 1423728

onnx/image_encoder.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affb6d6c6dbbbc3e361c260f796fb0b19b8e1a65b2eddb3502810bc55f34bf49
+size 375324672

onnx/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

onnx/text_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80bd8a56b6ddae9d80e13e781eae32b3a271576970a7d308079510db37a41f0
+size 708947

onnx/text_encoder.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2502df45e5838e5b5fff19cbc50d21ba10b3418f158cf68b78e97d0383f016c7
+size 90332160

onnx/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}