Upload folder using huggingface_hub

config.json

@@ -14,7 +14,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.33.0.dev0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 28996

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 sha256:58bf98db6c986fcc28a740909817f2b844ebb62f103455b62ad78a46a40dbec2
-size 522709397
+oid sha256:59a29c0d2f5638f088822810c430aafb255b31dbad9d71e2e52932e40e9cb99b
+size 433633812

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:626f08d3ed8f0bd3581f12c0c79625f3b9bb7103ef1b6aa49b88ce31d49efa2d
-size 132085067
+oid sha256:9884ecff392300993fd2fab427ffef6dfbb5cce047cb0ffff551f1623afcf76b
+size 109670506

quantize_config.json

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