Upload README.md

README.md

@@ -100,15 +100,22 @@ for i, query in enumerate(queries):
     print(f"Query: {query}")
     for j, doc in enumerate(documents):
         print(f" Similarity: {scores[i, j]:.4f} | Document {j}: {doc[:80]}...")
+```
+
+<details>
+
+<summary>See example output</summary>
+
+```
+Query: What is machine learning?
+ Similarity: 0.9063 | Document 0: Machine learning is a subset of ...
+ Similarity: 0.7287 | Document 1: Neural networks are trained ...
 
-# Query: What is machine learning?
-#  Similarity: 0.9063 | Document 0: Machine learning is a subset of ...
-#  Similarity: 0.7287 | Document 1: Neural networks are trained ...
-# 
-# Query: How does neural network training work?
-#  Similarity: 0.6725 | Document 0: Machine learning is a subset of ...
-#  Similarity: 0.8287 | Document 1: Neural networks are trained ...
+Query: How does neural network training work?
+ Similarity: 0.6725 | Document 0: Machine learning is a subset of ...
+ Similarity: 0.8287 | Document 1: Neural networks are trained ...
 ```
+</details>
 
 ## Transformers.js
 
@@ -123,7 +130,7 @@ You can then use the model to compute embeddings like this:
 import { AutoModel, AutoTokenizer, matmul } from "@huggingface/transformers";
 
 // Download from the 🤗 Hub
-const model_id = "onnx-community/mdbr-leaf-mt-ONNX";
+const model_id = "MongoDB/mdbr-leaf-mt";
 const tokenizer = await AutoTokenizer.from_pretrained(model_id);
 const model = await AutoModel.from_pretrained(model_id, {
     dtype: "fp32", // Options: "fp32" | "q8" | "q4"
@@ -216,13 +223,20 @@ similarities = model.similarity(query_embeds, doc_embeds)
 print('After MRL:')
 print(f"* Embeddings dimension: {query_embeds.shape[1]}")
 print(f"* Similarities: \n\t{similarities}")
+```
+
+<details>
+
+<summary>See example output</summary>
 
-# After MRL:
-# * Embeddings dimension: 256
-# * Similarities:
-#     tensor([[0.9164, 0.7219],
-#             [0.6682, 0.8393]], device='cuda:0')
 ```
+After MRL:
+* Embeddings dimension: 256
+* Similarities:
+    tensor([[0.9164, 0.7219],
+            [0.6682, 0.8393]], device='cuda:0')
+```
+</details>
 
 ## Vector Quantization
 Vector quantization, for example to `int8` or `binary`, can be performed as follows:
@@ -247,13 +261,20 @@ similarities = query_embeds.astype(int) @ doc_embeds.astype(int).T
 print('After quantization:')
 print(f"* Embeddings type: {query_embeds.dtype}")
 print(f"* Similarities: \n{similarities}")
+```
 
-# After quantization:
-# * Embeddings type: int8
-# * Similarities:
-#   [[2202032 1422868]
-#    [1421197 1845580]]
+<details>
+
+<summary>See example output</summary>
+
+```
+After quantization:
+* Embeddings type: int8
+* Similarities:
+   [[2202032 1422868]
+    [1421197 1845580]]
 ```
+</details>
 
 # Evaluation