Hugging Face's logo

Intel
/
roberta-large-mnli-int8-static-inc

Text Classification
Transformers
PyTorch
roberta
int8
Intel® Neural Compressor
neural-compressor
PostTrainingStatic
Inference Endpoints
Model card Files Community
echarlaix HF staff commited on
Commit
9a7c89c
•
1 Parent(s): d3e5af4

fix code snippet

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -33,8 +33,8 @@ The linear modules **roberta.encoder.layer.16.output.dense**, **roberta.encoder.
33
  ### Load with Intel® Neural Compressor:
34
 
35
  ```python
36
- from optimum.intel.neural_compressor import IncQuantizedModelForSequenceClassification
37
 
38
  model_id = "Intel/roberta-base-squad2-int8-static"
39
- int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(model_id)
40
  ```
33
  ### Load with Intel® Neural Compressor:
34
 
35
  ```python
36
+ from optimum.intel import INCModelForSequenceClassification
37
 
38
  model_id = "Intel/roberta-base-squad2-int8-static"
39
+ int8_model = INCModelForSequenceClassification.from_pretrained(model_id)
40
  ```