Upload folder using huggingface_hub

config.json

@@ -26,7 +26,7 @@
   "num_memory_blocks": 0,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.33.0.dev0",
   "type_vocab_size": 2,
   "vocab_size": 30000
 }

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a8c4bc0449c2759a5ac8d0ca7b81cf1f9b91f52030bfbf68c5eed58bc027f0c
-size 60630804
+oid sha256:3c0ae7eb336bc54e6abcb07e2dc21838ee86eda1f5bbc21d484aadc6d9de196b
+size 45270931

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07bd4e6c0a399201c1e0f16c62cec5b536041cff31895455a46114c84c449063
-size 44212034
+oid sha256:636b4995540f04f548f3e3651e9ad606461d09f348c469341293516fe369adab
+size 40221526

quantize_config.json

@@ -0,0 +1,31 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "ReduceMean",
+                "Cast",
+                "Add",
+                "Tanh",
+                "Pow",
+                "Reshape",
+                "Shape",
+                "Sqrt",
+                "Sub",
+                "Slice",
+                "Mul",
+                "Transpose",
+                "Constant",
+                "Softmax",
+                "MatMul",
+                "Identity",
+                "Unsqueeze",
+                "Concat",
+                "Div",
+                "Gather"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}