echarlaix HF staff commited on
Commit
e916825
1 Parent(s): 9abd552

Fix loading instructions

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -30,10 +30,10 @@ The original fp32 model comes from the fine-tuned model [Intel/bert-base-uncased
30
  ### Load with optimum:
31
 
32
  ```python
33
- from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification
34
- int8_model = IncQuantizedModelForSequenceClassification(
35
- 'Intel/bert-base-uncased-mrpc-int8-qat',
36
- )
37
  ```
38
 
39
  ### Training hyperparameters
 
30
  ### Load with optimum:
31
 
32
  ```python
33
+ from optimum.intel import INCModelForSequenceClassification
34
+
35
+ model_id = "Intel/bert-base-uncased-mrpc-int8-qat"
36
+ int8_model = INCModelForSequenceClassification.from_pretrained(model_id)
37
  ```
38
 
39
  ### Training hyperparameters