echarlaix HF staff commited on
Commit
47326f3
1 Parent(s): 1282d76

update loading instructions

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -50,10 +50,10 @@ The linear module **roberta.encoder.layer.6.attention.self.query** falls back to
50
  #### Load with Intel® Neural Compressor:
51
 
52
  ```python
53
- from optimum.intel.neural_compressor import IncQuantizedModelForSequenceClassification
54
 
55
  model_id = "Intel/camembert-base-mrpc-int8-dynamic"
56
- int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(model_id)
57
  ```
58
 
59
  ### ONNX
 
50
  #### Load with Intel® Neural Compressor:
51
 
52
  ```python
53
+ from optimum.intel import INCModelForSequenceClassification
54
 
55
  model_id = "Intel/camembert-base-mrpc-int8-dynamic"
56
+ int8_model = INCModelForSequenceClassification.from_pretrained(model_id)
57
  ```
58
 
59
  ### ONNX