Upload folder using huggingface_hub

.gitattributes

@@ -41,3 +41,4 @@ onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
 onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
 onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
 onnx/decoder_model_merged_quantized.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/q1/decoder_model_merged_quantized.onnx.data filter=lfs diff=lfs merge=lfs -text

onnx/.ipynb_checkpoints/quantize_config-checkpoint.json

@@ -0,0 +1,41 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "use_external_data_format": true,
+    "per_model_config": {
+        "decoder_model_merged": {
+            "op_types": [
+                "Cast",
+                "Sigmoid",
+                "If",
+                "Shape",
+                "Gather",
+                "Squeeze",
+                "Pow",
+                "Sub",
+                "Identity",
+                "Unsqueeze",
+                "MatMul",
+                "ReduceMean",
+                "Constant",
+                "Equal",
+                "Sqrt",
+                "Expand",
+                "Add",
+                "Range",
+                "Less",
+                "Div",
+                "ConstantOfShape",
+                "Where",
+                "Transpose",
+                "Mul",
+                "Slice",
+                "Softmax",
+                "Neg",
+                "Concat",
+                "Reshape"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

onnx/decoder_model_merged_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390640ee46632eb998ed966347c2f6acfddad5ea04aad9e7f9e528d241dacf0c
-size 19045741
+oid sha256:289772dc7b8a483e82ca0232aab62d166923f9ffe916109e9dd73d16f5c95525
+size 12084802

onnx/decoder_model_merged_quantized.onnx.data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d312201a36ec7d97cac2fc87c664ef0ec16a681f55ec013b9e3ce383904411e4
+oid sha256:3a0fd9d4b0c3fd0bce14531cd8f06ae7f2ab68bd5a84c0ae3a5be12e9de0d9a0
 size 6739214336

onnx/q1/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390640ee46632eb998ed966347c2f6acfddad5ea04aad9e7f9e528d241dacf0c
+size 19045741

onnx/q1/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

@@ -1,6 +1,6 @@
 {
-    "per_channel": true,
-    "reduce_range": true,
+    "per_channel": false,
+    "reduce_range": false,
     "use_external_data_format": true,
     "per_model_config": {
         "decoder_model_merged": {