Intel
/

bert-base-uncased-squad-int8-static-inc

Question Answering Transformers PyTorch

bert int8 Intel® Neural Compressor neural-compressor PostTrainingStatic Inference Endpoints

Model card Files Files and versions Community

echarlaix HF staff commited on Oct 26, 2022

Commit

8715481

•

1 Parent(s): 2018193

Update model card

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -3,6 +3,7 @@ license: apache-2.0
 tags:
 - int8
 - Intel® Neural Compressor
 - PostTrainingStatic
 datasets:
 - squad
@@ -32,8 +33,8 @@ The linear modules **bert.encoder.layer.2.intermediate.dense**, **bert.encoder.l
 ### Load with Intel® Neural Compressor:
 ```python
-from neural_compressor.utils.load_huggingface import OptimizedModel
-int8_model = OptimizedModel.from_pretrained(
-    'Intel/bert-base-uncased-squad-int8-static',
 )
 ```

 tags:
 - int8
 - Intel® Neural Compressor
+- neural-compressor
 - PostTrainingStatic
 datasets:
 - squad
 ### Load with Intel® Neural Compressor:
 ```python
+from optimum.intel.neural_compressor import IncQuantizedModelForQuestionAnswering
+int8_model = IncQuantizedModelForQuestionAnswering.from_pretrained(
+    "Intel/bert-base-uncased-squad-int8-static",
 )
 ```