Upload 8 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "TaylorAI/bge-micro",
+  "_name_or_path": "Mihaiii/Kyurem",
   "architectures": [
     "BertModel"
   ],
@@ -23,7 +23,6 @@
   "num_hidden_layers": 3,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "torch_dtype": "float16",
   "transformers_version": "4.40.1",
   "type_vocab_size": 2,
   "use_cache": true,

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c779d76ee87075794412db4c0bab996f9cac4dbdda79009d5daca5e7364f27
+size 69035106

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c4b2bcc49d74156a96f9c76e4de57329550618dd11d60bc3039ef4f80a5da9
+size 17452601

quantize_config.json

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