Intel
/

bert-base-uncased-CoLA-int8-inc

Text Classification

text-classfication

Intel® Neural Compressor

PostTrainingStatic

Inference Endpoints

Model card Files Files and versions Community

violetch24 commited on May 11, 2023

Commit

5f1155e

·

1 Parent(s): 654df1f

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ The original fp32 model comes from the fine-tuned model [Intel/bert-base-uncased
 |   |INT8|FP32|
 |---|:---:|:---:|
 | **Accuracy (eval-f1)** |0.5451|0.5339|
-| **Model size (MB)**  |388|438|
 #### Load with optimum:

 |   |INT8|FP32|
 |---|:---:|:---:|
 | **Accuracy (eval-f1)** |0.5451|0.5339|
+| **Model size (MB)**  |112|438|
 #### Load with optimum: