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": "4.29.2",
+  "transformers_version": "4.33.0.dev0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 119547

generation_config.json

@@ -1,5 +1,5 @@
 {
   "_from_model_config": true,
   "pad_token_id": 0,
-  "transformers_version": "4.29.2"
+  "transformers_version": "4.33.0.dev0"
 }

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3242fec81a4789bb48528b8f23d5b0fb8edda8e3eecb5467151895a5cbead000
-size 1079416949
+oid sha256:50b9295fd51d23948cf0dc652c478eccfdc62e28aef115c4ffdec60bbd168903
+size 712168690

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd70983b2aa6e56cd671d8a59caf0f6a39c05d5c06ad6ddf8085bd9e5e0ea7d
-size 271986364
+oid sha256:42d4a69e276e04bffeec2ec3830e9f43bf057f6f364c6481986dcc4705c46f30
+size 179575879

quantize_config.json

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