Intel
/

roberta-base-squad2-int8-static-inc

Intel® Neural Compressor

PostTrainingStatic

Inference Endpoints

Model card Files Files and versions Community

lvkaokao commited on Aug 30, 2022

Commit

b4d95a9

•

1 Parent(s): a159661

update README.md.

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ The calibration dataloader is the train dataloader. The default calibration samp
 The linear modules **roberta.encoder.layer.7.output.dense**, **roberta.encoder.layer.8.output.dense**, **roberta.encoder.layer.9.output.dense**, fall back to fp32 for less than 1% relative accuracy loss.
-### Test result
 |   |INT8|FP32|
 |---|:---:|:---:|

 The linear modules **roberta.encoder.layer.7.output.dense**, **roberta.encoder.layer.8.output.dense**, **roberta.encoder.layer.9.output.dense**, fall back to fp32 for less than 1% relative accuracy loss.
+### Evaluation result
 |   |INT8|FP32|
 |---|:---:|:---:|