Hugging Face's logo

Intel
/
distilbert-base-uncased-finetuned-conll03-english-int8-static-inc

Token Classification
Transformers
PyTorch
English
distilbert
token-classfication
int8
Intel® Neural Compressor
PostTrainingStatic
Eval Results
Inference Endpoints
Model card Files Community
xinhe commited on
Commit
73ca055
·
1 Parent(s): 8bdbbe7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -42,7 +42,7 @@ The calibration dataloader is the train dataloader. The default calibration samp
42
  | **Accuracy (eval-accuracy)** |0.9859|0.9882|
43
  | **Model size (MB)** |64.5|253|
44
 
45
- ### Load with Intel® Neural Compressor (build from source):
46
 
47
  ```python
48
  from neural_compressor.utils.load_huggingface import OptimizedModel
 
42
  | **Accuracy (eval-accuracy)** |0.9859|0.9882|
43
  | **Model size (MB)** |64.5|253|
44
 
45
+ ### Load with Intel® Neural Compressor:
46
 
47
  ```python
48
  from neural_compressor.utils.load_huggingface import OptimizedModel