Update README.md

README.md

@@ -34,7 +34,7 @@ This model conducts unstructured magnitude pruning, quantization and distillatio
 It achieves the following results on the evaluation set:
 - Torch loss: 0.4116
 - Torch accuracy: 0.9140
-- OpenVINO accuracy: 0.9106
+- OpenVINO IR accuracy: 0.9106
 - Sparsity in transformer block linear layers: 0.80
 
 ## Setup