Add new SentenceTransformer model

README.md

@@ -19,7 +19,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps
 <!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
 - **Maximum Sequence Length:** 512 tokens
 - **Output Dimensionality:** 768 dimensions
-- **Similarity Function:** Cosine Similarity
+- **Similarity Function:** Dot Product
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
 <!-- - **License:** Unknown -->
@@ -68,9 +68,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.9583, 0.9074],
-#         [0.9583, 1.0000, 0.9121],
-#         [0.9074, 0.9121, 1.0000]])
+# tensor([[743.6603, 712.7500, 674.8392],
+#         [712.7500, 743.7998, 678.3881],
+#         [674.8391, 678.3880, 743.6827]])
 ```
 
 <!--

config_sentence_transformers.json

@@ -10,5 +10,5 @@
     "document": ""
   },
   "default_prompt_name": null,
-  "similarity_fn_name": "cosine"
+  "similarity_fn_name": "dot"
 }