onnx files

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1def61ab7448b9edb4bce098d141e52d1435c4da2ab69a508f196d3837629b
+oid sha256:9049ec114cbaba38be789bca09806b055e337c7b9956aa0b71e64cec132a55a6
 size 98500900

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c090bf9d61b39c4f4d3d56eb74279580bcaae1ea584d16b162c26a2300b78e7
+size 99056240

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6297e6e58a4c1682a88f47154db3c528b61d773fb5764e051d2c79527b2a875
+oid sha256:be3947abc8a98a2f314fc78aeba0472c17d4a5038d370b453b8bd1d3cb073aee
 size 26510183

quantize_config.json

@@ -4,26 +4,26 @@
     "per_model_config": {
         "model": {
             "op_types": [
-                "Relu",
-                "ConstantOfShape",
-                "Softmax",
-                "Gather",
                 "Div",
-                "MatMul",
-                "Add",
-                "Mul",
-                "Reshape",
-                "Cast",
-                "Gemm",
-                "Transpose",
-                "Constant",
+                "ConstantOfShape",
                 "Shape",
+                "Gemm",
                 "Slice",
+                "Softmax",
+                "Cast",
+                "Add",
+                "Relu",
+                "Sub",
                 "Pad",
+                "Reshape",
+                "MatMul",
                 "Unsqueeze",
+                "Identity",
+                "Transpose",
+                "Mul",
                 "Concat",
-                "Sub",
-                "Identity"
+                "Gather",
+                "Constant"
             ],
             "weight_type": "QInt8"
         }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7680c119d9c958c37db00490731d92512d729e3c266e211ab88eac5b7eee8c5
+oid sha256:cd19049a43b80f29f3ffd49e3f571152f57c133923a20008c7521f554347e273
 size 5176