Upload folder using huggingface_hub

.gitattributes

@@ -45,3 +45,4 @@ onnx/q1/decoder_model_merged_quantized.onnx.data filter=lfs diff=lfs merge=lfs -
 onnx/decoder_model_merged_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
 onnx/decoder_model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
 onnx/decoder_with_past_model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text

onnx/decoder_model_merged_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289772dc7b8a483e82ca0232aab62d166923f9ffe916109e9dd73d16f5c95525
-size 12084802
+oid sha256:210c6485f34cc1c35daa38072b29cb540c7dc7c04326cfd5b81c1429368398e3
+size 19045741

onnx/decoder_model_merged_quantized.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d312201a36ec7d97cac2fc87c664ef0ec16a681f55ec013b9e3ce383904411e4
+size 6739214336

onnx/quantize_config.json

@@ -1,39 +1,39 @@
 {
-    "per_channel": false,
-    "reduce_range": false,
+    "per_channel": true,
+    "reduce_range": true,
     "use_external_data_format": true,
     "per_model_config": {
         "decoder_model_merged": {
             "op_types": [
-                "Cast",
-                "Sigmoid",
+                "Slice",
+                "Sqrt",
+                "Less",
                 "If",
                 "Shape",
-                "Gather",
-                "Squeeze",
-                "Pow",
+                "Transpose",
+                "Range",
                 "Sub",
-                "Identity",
-                "Unsqueeze",
-                "MatMul",
-                "ReduceMean",
-                "Constant",
+                "Concat",
+                "Squeeze",
+                "Cast",
+                "Neg",
                 "Equal",
-                "Sqrt",
-                "Expand",
                 "Add",
-                "Range",
-                "Less",
+                "Pow",
+                "Reshape",
+                "Identity",
                 "Div",
-                "ConstantOfShape",
+                "Constant",
+                "Gather",
+                "Softmax",
+                "Sigmoid",
+                "ReduceMean",
                 "Where",
-                "Transpose",
                 "Mul",
-                "Slice",
-                "Softmax",
-                "Neg",
-                "Concat",
-                "Reshape"
+                "Expand",
+                "MatMul",
+                "Unsqueeze",
+                "ConstantOfShape"
             ],
             "weight_type": "QInt8"
         }