Update README.md

README.md

@@ -43,13 +43,23 @@ pip install -U sentence-transformers
 Then you can use the model like this:
 
 ```python
-from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
+from sentence_transformers import SentenceTransformer, util
+sentences = ["This is a Norwegian boy", "Dette er en norsk gutt"]
 
 model = SentenceTransformer('NbAiLab/nb-sbert')
 embeddings = model.encode(sentences)
 print(embeddings)
 
+# Compute cosine-similarities with sentence transformers
+cosine_scores = util.cos_sim(embeddings[0],embeddings[1])
+print(cosine_scores)
+
+# Compute cosine-similarities with SciPy
+from scipy import spatial
+scipy_cosine_scores = 1 - spatial.distance.cosine(embeddings[0],embeddings[1])
+print(scipy_cosine_scores)
+
+# Both should give 0.8250 in the example above.
 
 ```
 
@@ -71,7 +81,7 @@ def mean_pooling(model_output, attention_mask):
 
 
 # Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
+sentences = ["This is a Norwegian boy", "Dette er en norsk gutt"]
 
 # Load model from HuggingFace Hub
 tokenizer = AutoTokenizer.from_pretrained('NbAiLab/nb-sbert')
@@ -85,10 +95,17 @@ with torch.no_grad():
     model_output = model(**encoded_input)
 
 # Perform pooling. In this case, mean pooling.
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print(embeddings)
+
+# Compute cosine-similarities with SciPy
+from scipy import spatial
+scipy_cosine_scores = 1 - spatial.distance.cosine(embeddings[0],embeddings[1])
+print(scipy_cosine_scores)
+
+# This should give 0.8250 in the example above.
 
-print("Sentence embeddings:")
-print(sentence_embeddings)
 ```