quantized v1.5 model

.gitignore

@@ -0,0 +1,2 @@
+# macOS
+.DS_Store

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/BAAI_bge-base-en/",
+  "_name_or_path": "onnx-v1.5",
   "architectures": [
     "BertModel"
   ],
@@ -24,8 +24,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.30.0",
+  "transformers_version": "4.33.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

onnx

@@ -0,0 +1 @@
+onnx-v1.5

onnx-v1.5/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc579acdba21c253c62a9bf866891355a63ffa3442b52c8a37d75b2ccb91848
+size 435811539

onnx-v1.5/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d996808c4539936ecc55be24dc3ecd8c36de1ebfcc461325f5cb4d947f7483
+size 109706513

onnx-v1/ort_config.json

@@ -0,0 +1,35 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "optimum_version": "1.12.0",
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "MatMul",
+      "Attention",
+      "LSTM",
+      "Gather",
+      "Transpose",
+      "EmbedLayerNormalization"
+    ],
+    "per_channel": false,
+    "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": "4.33.0",
+  "use_external_data_format": false
+}