Upload folder using huggingface_hub

config.json

@@ -19,7 +19,7 @@
   "num_hidden_layers": 6,
   "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 sha256:06a551bee85d05964b11bb02ca6cf699978fdfb34ff74eef1048e54efe855e7f
-size 483243605
+oid sha256:323fe48b2c838dc62c21b07b7681634031b47218553afd1bbd81eaa5dade5393
+size 328829650

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5922de9bf6132632f545b4261c61f26f0051d22c4397210db2fa92eecf9ab5
-size 121825755
+oid sha256:83ace14b3376ef74309dc5d4703471ebe1946fe796c93a0e8fc892f455ffb473
+size 82970431

quantize_config.json

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