Commit
•
cf5ceed
1
Parent(s):
ceaa7d3
update int8 onnx model and readme
Browse filesSigned-off-by: dujun <jun.du@intel.com>
- README.md +2 -2
- model.onnx +2 -2
README.md
CHANGED
|
@@ -27,8 +27,8 @@ The original fp32 model comes from the fine-tuned model [Alireza1044/albert-base
|
|
| 27 |
|
| 28 |
| |INT8|FP32|
|
| 29 |
|---|:---:|:---:|
|
| 30 |
-
| **Accuracy (eval-accuracy)** |0.
|
| 31 |
-
| **Model size (MB)** |
|
| 32 |
|
| 33 |
|
| 34 |
#### Load ONNX model:
|
|
|
|
| 27 |
|
| 28 |
| |INT8|FP32|
|
| 29 |
|---|:---:|:---:|
|
| 30 |
+
| **Accuracy (eval-accuracy)** |0.9186|0.9232|
|
| 31 |
+
| **Model size (MB)** |59|45|
|
| 32 |
|
| 33 |
|
| 34 |
#### Load ONNX model:
|
model.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 sha256:8750fc65ffae69178c56f574e2cc2353a13d74dad952c2865cad5203fce849c2
|
| 3 |
+
size 61587971
|