Upload folder using huggingface_hub
Browse files- onnx/model_quantized.onnx +2 -2
- ort_config.json +2 -3
onnx/model_quantized.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a3bda057b541217345984a0574ca39c22eba4ef02daf1656cc1033ab1fc4f20
|
| 3 |
+
size 24417500
|
ort_config.json
CHANGED
|
@@ -8,11 +8,10 @@
|
|
| 8 |
"format": "QOperator",
|
| 9 |
"is_static": false,
|
| 10 |
"mode": "IntegerOps",
|
| 11 |
-
"nodes_to_exclude": [
|
| 12 |
-
"Conv_quant"
|
| 13 |
-
],
|
| 14 |
"nodes_to_quantize": [],
|
| 15 |
"operators_to_quantize": [
|
|
|
|
| 16 |
"MatMul",
|
| 17 |
"Attention",
|
| 18 |
"LSTM",
|
|
|
|
| 8 |
"format": "QOperator",
|
| 9 |
"is_static": false,
|
| 10 |
"mode": "IntegerOps",
|
| 11 |
+
"nodes_to_exclude": [],
|
|
|
|
|
|
|
| 12 |
"nodes_to_quantize": [],
|
| 13 |
"operators_to_quantize": [
|
| 14 |
+
"Conv",
|
| 15 |
"MatMul",
|
| 16 |
"Attention",
|
| 17 |
"LSTM",
|