Upload 8 files

config.json

@@ -17,7 +17,6 @@
   "num_hidden_layers": 3,
   "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:f7e902e7a8cee38fef914920d1a2abe67496b43f5f42497bad593dcde3a6bab7
+size 69035106

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27fb89c260980d7ce2ab5f85fe1cbdc5c23146fdb6b16107586fa804d1094e37
+size 17452601

quantize_config.json

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