Upload folder using huggingface_hub

config.json

@@ -18,7 +18,7 @@
   "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:e0aa19d140ec6dac81b11389347d300288210264aea801d00291a1122948c953
-size 522709397
+oid sha256:b8d9bfb5975103e93dd25fbc5318bdbfdbb65b7baa6f7a03697d66232380a516
+size 433633812

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c0b8b13eff4d0760c762880502d0fa39ae960697d021f5d2925632b88022efc
-size 132085068
+oid sha256:9a213cb783bb2080b6bfce0df69e5030e8704aa5226bb9a236d29c7b717cec87
+size 109670507

quantize_config.json

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