Update README.md

README.md

@@ -115,10 +115,10 @@ Note that multilingual NLI models are capable of classifying NLI texts without r
 in the specific language (cross-lingual transfer). This means that the model is also able of doing NLI on 
 the other languages it was training on, but performance is most likely lower than for those languages available in XNLI.
 
-The average XNLI performance of multilingual-MiniLM-L6 reported in the paper is 0.68 ([see table 11](https://arxiv.org/pdf/2002.10957.pdf)). 
-This reimplementation has an average performance of 0.713. 
+The average XNLI performance of multilingual-MiniLM-L12 reported in the paper is 0.711 ([see table 11](https://arxiv.org/pdf/2002.10957.pdf)). 
+This reimplementation has an average performance of 0.75. 
 This increase in performance is probably thanks to the addition of MNLI in the training data and this model was distilled from 
-XLM-RoBERTa-large instead of -base (multilingual-MiniLM-L6-v2). 
+XLM-RoBERTa-large instead of -base (multilingual-MiniLM-L12-v2).