Intel
/

MiniLM-L12-H384-uncased-mrpc-int8-static-inc

Text Classification

text-classfication

Intel® Neural Compressor

PostTrainingStatic

Inference Endpoints

Model card Files Files and versions Community

yuwenz commited on Feb 3, 2023

Commit

ec9cbc8

·

1 Parent(s): 33749c1

update README

Signed-off-by: yuwenzho <[email protected]>

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -25,14 +25,14 @@ The calibration dataloader is the train dataloader. The default calibration samp
 The linear module **bert.encoder.layer.6.attention.self.key** falls back to fp32 to meet the 1% relative accuracy loss.
-### Test result
 |   |INT8|FP32|
 |---|:---:|:---:|
 | **Accuracy (eval-f1)** |0.9039|0.9097|
 | **Model size (MB)**  |33.5|127|
-### Load with optimum:
 ```python
 from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification

 The linear module **bert.encoder.layer.6.attention.self.key** falls back to fp32 to meet the 1% relative accuracy loss.
+#### Test result
 |   |INT8|FP32|
 |---|:---:|:---:|
 | **Accuracy (eval-f1)** |0.9039|0.9097|
 | **Model size (MB)**  |33.5|127|
+#### Load with optimum:
 ```python
 from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification