Upload folder using huggingface_hub

config.json

@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.33.0.dev0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac9a8e10c9c45461d3b8cb1acd2def1f4739f2bc98f6f749383d2d78b647002
-size 653487692
+oid sha256:53c6d511973549647084037a54405b08ee4b138767461497b88a4d1a85f720d6
+size 499073736

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242f6b797762861f1e5608482533e0725773c998d41888ea62ac0f340cad3564
-size 164967138
+oid sha256:7aea99df87679b6efdece225e4d59cc1d72155d81a7ee13cb713ef2d8e7cfa5c
+size 126111809

quantize_config.json

@@ -0,0 +1,36 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Transpose",
+                "Mul",
+                "Sub",
+                "Concat",
+                "Sqrt",
+                "Gather",
+                "ConstantOfShape",
+                "Not",
+                "ReduceMean",
+                "Constant",
+                "Where",
+                "Unsqueeze",
+                "Erf",
+                "Div",
+                "CumSum",
+                "Pow",
+                "MatMul",
+                "Expand",
+                "Slice",
+                "Equal",
+                "Add",
+                "Cast",
+                "Shape",
+                "Softmax",
+                "Reshape"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}