Upload 8 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "TaylorAI/gte-tiny",
+  "_name_or_path": "Mihaiii/gte-micro-v3",
   "architectures": [
     "BertModel"
   ],
@@ -17,8 +17,7 @@
   "num_hidden_layers": 3,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.39.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21882957abb750b434723c467420be9da63badd50bba59a2aefcf8d50fdbd622
+size 69035106

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cace3bdde4e0fa3d6bcdb527db019759578971c249c25cc1184e0b459ed5f026
+size 17452600

quantize_config.json

@@ -0,0 +1,30 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Cast",
+                "Erf",
+                "Concat",
+                "MatMul",
+                "Add",
+                "Div",
+                "Transpose",
+                "Reshape",
+                "Sub",
+                "Gather",
+                "Mul",
+                "Sqrt",
+                "Shape",
+                "Slice",
+                "Unsqueeze",
+                "ReduceMean",
+                "Constant",
+                "Pow",
+                "Softmax"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}