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 sha256:531ee3021dbd2dab6961615185c321e405beb1bc93a006503dd41726973d2021
-size 83301256
+oid sha256:ae56917c8df36bced2a7b197ead8006bf47d7f4c771c015badd55f877c6f1c26
+size 67941384

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3851bd633c37472ce90602a98f0d5cefebf1f5c1537121924b39ffcf95ee71
-size 72328456
+oid sha256:d422074eb8acca46b98bd4761ce4b4e14eab86d3fc87dcd7d4d7b3192f0efd34
+size 68337949

quantize_config.json

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