Upload folder using huggingface_hub

config.json

@@ -23,7 +23,7 @@
   "pooler_size_per_head": 128,
   "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
-  "transformers_version": "4.32.0.dev0",
+  "transformers_version": "4.33.0.dev0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 21128

generation_config.json

@@ -1,5 +1,5 @@
 {
   "_from_model_config": true,
   "pad_token_id": 0,
-  "transformers_version": "4.32.0.dev0"
+  "transformers_version": "4.33.0.dev0"
 }

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1913f6953fb0bce78650887048f598db5273bc5dc26dcd8c671611847b4d929a
-size 474336946
+oid sha256:624cc2492e0910b016c266ad0adcccfcea078c2ea3074f4fee781f5c553b4419
+size 409431844

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e6d3f08e6f1f387acbc84daf865611df477e4d448074556e83a466385edd198
-size 119929056
+oid sha256:918f5023c235d9667f543c81fe00f6a324c5c41b8c5e335db2ce7ed6e249b739
+size 103596410

quantize_config.json

@@ -4,25 +4,25 @@
     "per_model_config": {
         "model": {
             "op_types": [
-                "Shape",
-                "Unsqueeze",
-                "Sub",
                 "Pow",
-                "MatMul",
                 "Div",
                 "Sqrt",
-                "Transpose",
+                "Concat",
+                "Softmax",
+                "Unsqueeze",
+                "Sub",
                 "Cast",
+                "ReduceMean",
+                "Reshape",
                 "Gather",
+                "Transpose",
+                "Mul",
                 "Erf",
                 "Constant",
-                "Slice",
-                "Softmax",
+                "Shape",
                 "Add",
-                "ReduceMean",
-                "Mul",
-                "Concat",
-                "Reshape"
+                "MatMul",
+                "Slice"
             ],
             "weight_type": "QInt8"
         }