Update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "TaylorAI/bge-micro-v2",
+  "_name_or_path": "avsolatorio/GIST-small-Embedding-v0",
   "architectures": [
     "BertModel"
   ],
@@ -20,7 +20,7 @@
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 3,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "transformers_version": "4.38.1",

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffbd7473c28b676a2ea3998a1eded2b212daa5decffda02855f6daf1897c3e4a
-size 69035107
+oid sha256:8c95502dc23d4ffb50a81d3838f721abde71509982d720d355ce52c0cdfe2dfe
+size 133093492

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff15efa54b99d96aef73e864e94a19af3deaccd64b79cd5953cbb0ee3f65229e
-size 17452161
+oid sha256:45b972073570f3af92b90b708ec580d63cca87654e2d5e7ccb2cf560aa881bf3
+size 34014427

quantize_config.json

@@ -4,25 +4,25 @@
     "per_model_config": {
         "model": {
             "op_types": [
-                "Mul",
+                "Transpose",
                 "Add",
-                "Unsqueeze",
+                "Concat",
+                "Shape",
+                "Mul",
                 "Reshape",
-                "Sub",
-                "Constant",
+                "Gather",
                 "Div",
-                "Concat",
-                "Transpose",
+                "Constant",
+                "Sub",
                 "Pow",
+                "Slice",
+                "Sqrt",
                 "Erf",
-                "Softmax",
                 "Cast",
-                "Sqrt",
-                "Slice",
+                "Softmax",
+                "Unsqueeze",
                 "ReduceMean",
-                "Shape",
-                "MatMul",
-                "Gather"
+                "MatMul"
             ],
             "weight_type": "QInt8"
         }

special_tokens_map.json

@@ -1,11 +1,4 @@
 {
-  "additional_special_tokens": [
-    "[PAD]",
-    "[UNK]",
-    "[CLS]",
-    "[SEP]",
-    "[MASK]"
-  ],
   "cls_token": {
     "content": "[CLS]",
     "lstrip": false,

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "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

@@ -41,31 +41,17 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "[PAD]",
-    "[UNK]",
-    "[CLS]",
-    "[SEP]",
-    "[MASK]"
-  ],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 512,
-  "model_max_length": 1000000000000000019884624838656,
+  "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]"
 }