Intel
/

bart-large-cnn-int8-dynamic-inc

Text2Text Generation

Intel® Neural Compressor

neural-compressor

PostTrainingDynamic

Inference Endpoints

Model card Files Files and versions Community

echarlaix HF staff commited on Mar 22

Commit

7050066

•

1 Parent(s): a6c0703

update loading instructions

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -52,8 +52,8 @@ Below linear modules (40/193) are fallbacked to fp32 for less than 1% relative a
 ### Load with optimum:
 ```python
-from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSeq2SeqLM
-int8_model = IncQuantizedModelForSeq2SeqLM.from_pretrained(
-    'Intel/bart-large-cnn-int8-dynamic',
-)
-```

 ### Load with optimum:
 ```python
+from optimum.intel import INCModelForSeq2SeqLM
+model_id = "Intel/bart-large-cnn-int8-dynamic"
+int8_model = INCModelForSeq2SeqLM.from_pretrained(model_id)
+```