Update README.md

README.md

@@ -30,7 +30,7 @@ The original fp32 model comes from the fine-tuned model [Intel/bert-base-uncased
 | **Accuracy (eval-f1)** |0.9153|0.9042|
 | **Model size (MB)**  |174|418|
 
-### Load with nlp-toolkit:
+### Load with Intel® Neural Compressor (build from source):
 
 ```python
 from neural_compressor.utils.load_huggingface import OptimizedModel