Intel
/

roberta-base-squad2-int8-static-inc

Intel® Neural Compressor

PostTrainingStatic

Inference Endpoints

Model card Files Files and versions Community

echarlaix HF staff commited on Mar 21

Commit

ced23b6

•

1 Parent(s): bab0264

update loading instructions

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -32,8 +32,8 @@ The linear modules **roberta.encoder.layer.7.output.dense**, **roberta.encoder.l
 ### Load with optimum:
 ```python
-from optimum.intel.neural_compressor.quantization import IncQuantizedModelForQuestionAnswering
-int8_model = IncQuantizedModelForQuestionAnswering.from_pretrained(
-    'Intel/roberta-base-squad2-int8-static',
-)
 ```

 ### Load with optimum:
 ```python
+from optimum.intel import INCModelForQuestionAnswering
+model_id = "Intel/roberta-base-squad2-int8-static"
+int8_model = INCModelForQuestionAnswering.from_pretrained(model_id)
 ```