Upload 8 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Mihaiii/test20",
+  "_name_or_path": "Mihaiii/test21",
   "architectures": [
     "BertModel"
   ],
@@ -23,7 +23,6 @@
   "num_hidden_layers": 2,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
   "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:d5eb8a6b1f2aceeb276e9dfea8febe3c6baa85e311acbb20eade2a73f2a39dc9
+size 61917599

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36929ab343eba467365fa7dbed355751472c0f4a4b0de1c308f6802a417ceb8b
+size 15612513

quantize_config.json

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