Update README.md

Fix bug in transformers example, because both vectors are 1-dimensional, the dim needs to be set to 0

README.md

@@ -192,7 +192,7 @@ embeddings = F.normalize(embeddings, p=2, dim=1)
 print(embeddings.shape)
 # torch.Size([2, 768])
 
-similarity = F.cosine_similarity(embeddings[0], embeddings[1])
+similarity = F.cosine_similarity(embeddings[0], embeddings[1], dim=0)
 print(similarity)
 # tensor(0.9118)
 ```