echarlaix HF staff commited on
Commit
ced23b6
1 Parent(s): bab0264

update loading instructions

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -32,8 +32,8 @@ The linear modules **roberta.encoder.layer.7.output.dense**, **roberta.encoder.l
32
  ### Load with optimum:
33
 
34
  ```python
35
- from optimum.intel.neural_compressor.quantization import IncQuantizedModelForQuestionAnswering
36
- int8_model = IncQuantizedModelForQuestionAnswering.from_pretrained(
37
- 'Intel/roberta-base-squad2-int8-static',
38
- )
39
  ```
 
32
  ### Load with optimum:
33
 
34
  ```python
35
+ from optimum.intel import INCModelForQuestionAnswering
36
+
37
+ model_id = "Intel/roberta-base-squad2-int8-static"
38
+ int8_model = INCModelForQuestionAnswering.from_pretrained(model_id)
39
  ```