Upload folder using huggingface_hub

config.json

@@ -20,7 +20,7 @@
   "output_past": true,
   "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": 250002

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:188c6b93577e6a112c6e99200ed11f0e2cff105b05e241fd9feed63f8807cc11
-size 1881470772
+oid sha256:f60fc6d14d071996bee0d007e9fd4eec15403bb5e7c48a6f17773c87311af163
+size 1113464750

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f942f71d623ffdd8d9c971c87fc6b9734918f300128a3bdb5ca0a545204ca0
-size 473560803
+oid sha256:f8547220520c540258aef930319fa6304a40cdb43c5c859b5ce5a3ee03c92d74
+size 280308773

quantize_config.json

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