Upload folder using huggingface_hub

config.json

@@ -18,6 +18,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.33.0.dev0",
   "vocab_size": 30522
 }

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7b2b46205ce8bb391016769769a0661bd7c561f9f521a61f34139a3dc67a959
-size 361843405
+oid sha256:8ca11af9a73c6ae6ac519c16cbce48331eb67fb3df64f8fccb52096c69a27872
+size 268079955

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e29287b95e16bdf37184dec897cb007ee6f2884a0bc6bb8b13df4e79584dbc
-size 91304570
+oid sha256:52ff4db0aaa896d9af790a1464373a77923dcd27d0479859f429598c888d8b09
+size 67710626

quantize_config.json

@@ -0,0 +1,33 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Add",
+                "Concat",
+                "Unsqueeze",
+                "Shape",
+                "Sub",
+                "Where",
+                "Softmax",
+                "Erf",
+                "Pow",
+                "Gather",
+                "Div",
+                "MatMul",
+                "Equal",
+                "Mul",
+                "Cast",
+                "Expand",
+                "Constant",
+                "Transpose",
+                "Slice",
+                "ReduceMean",
+                "Sqrt",
+                "Reshape"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}