Intel
/

bert-base-uncased-finetuned-swag-int8-static-inc

Multiple Choice Transformers PyTorch

English bert int8 Intel® Neural Compressor PostTrainingStatic Eval Results Inference Endpoints

Model card Files Files and versions Community

echarlaix HF staff commited on Oct 6, 2023

Commit

23ab442

•

1 Parent(s): 793cccf

fix

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -46,8 +46,8 @@ The linear modules **bert.encoder.layer.2.output.dense, bert.encoder.layer.5.int
 ### Load with optimum:
 ```python
-from optimum.intel.neural_compressor.quantization import IncQuantizedModelForMultipleChoice
-int8_model = IncQuantizedModelForMultipleChoice.from_pretrained(
-    'Intel/bert-base-uncased-finetuned-swag-int8-static',
-)
 ```

 ### Load with optimum:
 ```python
+from optimum.intel import INCModelForMultipleChoice
+model_id = "Intel/bert-base-uncased-finetuned-swag-int8-static"
+int8_model = INCModelForMultipleChoice.from_pretrained(model_id)
 ```