Update to match artifacts from Colab

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "_name_or_path": "onnx/model-optimized",
   "architectures": [
     "BertModel"
   ],
@@ -18,9 +18,8 @@
   "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.23.1",
+  "transformers_version": "4.30.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522
-}
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f6530b25541e6e793bd3bbd3ccbe340bf65e5202e9e83948f00b008ffa4aa1
+size 66488120

ort_config.json

@@ -0,0 +1,30 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "optimum_version": "1.8.8",
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "MatMul",
+      "Add"
+    ],
+    "per_channel": true,
+    "qdq_add_pair_to_weight": false,
+    "qdq_dedicated_pair": false,
+    "qdq_op_type_per_channel_support_to_axis": {
+      "MatMul": 1
+    },
+    "reduce_range": false,
+    "weights_dtype": "QInt8",
+    "weights_symmetric": true
+  },
+  "transformers_version": "4.30.2",
+  "use_external_data_format": false
+}

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 128
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -1,14 +1,13 @@
 {
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": "C:\\Users\\alvin/.cache\\huggingface\\hub\\models--sentence-transformers--all-MiniLM-L6-v2\\snapshots\\7dbbc90392e2f80f3d3c277d6e90027e55de9125\\special_tokens_map.json",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",