Hugging Face's logo

Intel
/
distilbert-base-uncased-finetuned-sst-2-english-int8-static-inc

Text Classification
Transformers
PyTorch
ONNX
English
distilbert
text-classfication
int8
neural-compressor
Intel® Neural Compressor
PostTrainingStatic
Eval Results
Inference Endpoints
Model card Files Community
2
xinhe commited on
Commit
b6e6083
•
1 Parent(s): a6fa906

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -33,7 +33,7 @@ The calibration dataloader is the train dataloader. The default calibration samp
33
  | **Accuracy (eval-accuracy)** |0.9037|0.9106|
34
  | **Model size (MB)** |65|255|
35
 
36
- ### Load with Intel® Neural Compressor:
37
 
38
  ```python
39
  from neural_compressor.utils.load_huggingface import OptimizedModel
 
33
  | **Accuracy (eval-accuracy)** |0.9037|0.9106|
34
  | **Model size (MB)** |65|255|
35
 
36
+ ### Load with Intel® Neural Compressor (build from source):
37
 
38
  ```python
39
  from neural_compressor.utils.load_huggingface import OptimizedModel