Upload README.md

README.md

@@ -96,12 +96,12 @@ for i, query in enumerate(queries):
         print(f" Similarity: {scores[i, j]:.4f} | Document {j}: {doc[:80]}...")
 
 # Query: What is machine learning?
-#  Similarity: 0.6908 | Document 0: Machine learning is a subset of ...
+#  Similarity: 0.6857 | Document 0: Machine learning is a subset of ...
 #  Similarity: 0.4598 | Document 1: Neural networks are trained ...
 # 
 # Query: How does neural network training work?
-#  Similarity: 0.4432 | Document 0: Machine learning is a subset of ...
-#  Similarity: 0.5794 | Document 1: Neural networks are trained ...
+#  Similarity: 0.4238 | Document 0: Machine learning is a subset of ...
+#  Similarity: 0.5723 | Document 1: Neural networks are trained ...
 ```
   
 ### Transformers Usage  
@@ -171,8 +171,8 @@ with torch.inference_mode():
 similarities = query_embeddings @ document_embeddings.T
 print(f"Similarities:\n{similarities}")
 # Similarities:
-#  tensor([[0.6908, 0.4598],
-#          [0.4432, 0.5794]])
+#  tensor([[0.6857, 0.4598],
+#          [0.4238, 0.5723]])
 ```   -->
   
 ### Asymmetric Retrieval Setup  
@@ -180,13 +180,13 @@ print(f"Similarities:\n{similarities}")
 `mdbr-leaf-ir` is *aligned* to [`snowflake-arctic-embed-m-v1.5`](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v1.5), the model it has been distilled from, making the asymmetric system below possible: 
   
 ```python  
-# Use a larger model for document encoding (one-time, at index time)  
-doc_model = SentenceTransformer("Snowflake/snowflake-arctic-embed-m-v1.5")  
-document_embeddings = doc_model.encode(documents)  
-  
 # Use mdbr-leaf-ir for query encoding (real-time, low latency)  
 query_model = SentenceTransformer("MongoDB/mdbr-leaf-ir")  
 query_embeddings = query_model.encode(queries, prompt_name="query")  
+
+# Use a larger model for document encoding (one-time, at index time)  
+doc_model = SentenceTransformer("Snowflake/snowflake-arctic-embed-m-v1.5")  
+document_embeddings = doc_model.encode(documents)  
   
 # Compute similarities  
 scores = query_model.similarity(query_embeddings, document_embeddings)  
@@ -215,8 +215,8 @@ print(f"* Similarities:\n\t{similarities}")
 # After MRL:
 # * Embeddings dimension: 256
 # * Similarities:
-# 	tensor([[0.7202, 0.5006],
-#           [0.4744, 0.6083]])
+# 	tensor([[0.7136, 0.4989],
+#           [0.4567, 0.6022]])
 ```
 
 ### Vector Quantization
@@ -248,8 +248,8 @@ print(f"* Similarities:\n{similarities}")
 # After quantization:
 # * Embeddings type: int8
 # * Similarities:
-#  [[119073  78877]
-#   [ 76174  99127]]
+#  [[118022  79111]
+#   [ 72961  98333]]
 ```
 
 ## Evaluation