Add new SentenceTransformer model (#3)

- Add new SentenceTransformer model (8b4c685c8970becdc74e51bcde44b007a7b6b407)
- Undo README changes (ad207b7b3d9f3a0b92fa4813457af703402d9cac)
- Update README outputs + dim (768 -> 1024) (96fbb87a02f10fea60382bebdfed945b381fe776)


Co-authored-by: Tom Aarsen <[email protected]>

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -2950,12 +2950,12 @@ doc_embeddings = model.encode([
     "search_document: TSNE is a dimensionality reduction algorithm created by Laurens van Der Maaten",
 ])
 print(query_embeddings.shape, doc_embeddings.shape)
-# (2, 768) (1, 768)
+# (2, 1024) (1, 1024)
 
 similarities = model.similarity(query_embeddings, doc_embeddings)
 print(similarities)
-# tensor([[0.7214],
-#         [0.3260]])
+# tensor([[0.6518],
+#         [0.4237]])
 ```
 
 <details><summary>Click to see Sentence Transformers usage with Matryoshka Truncation</summary>
@@ -2979,8 +2979,8 @@ print(query_embeddings.shape, doc_embeddings.shape)
 
 similarities = model.similarity(query_embeddings, doc_embeddings)
 print(similarities)
-# tensor([[0.7759],
-#         [0.3419]])
+# tensor([[0.6835],
+#         [0.3982]])
 ```
 
 Note the small differences compared to the full 1024-dimensional similarities.
@@ -3023,12 +3023,12 @@ query_embeddings = F.normalize(query_embeddings, p=2, dim=1)
 doc_embeddings = mean_pooling(documents_outputs, encoded_documents["attention_mask"])
 doc_embeddings = F.normalize(doc_embeddings, p=2, dim=1)
 print(query_embeddings.shape, doc_embeddings.shape)
-# torch.Size([2, 768]) torch.Size([1, 768])
+# torch.Size([2, 1024]) torch.Size([1, 1024])
 
 similarities = query_embeddings @ doc_embeddings.T
 print(similarities)
-# tensor([[0.7214],
-#         [0.3260]])
+# tensor([[0.6518],
+#         [0.4237]])
 ```
 
 <details><summary>Click to see Transformers usage with Matryoshka Truncation</summary>
@@ -3076,11 +3076,11 @@ print(query_embeddings.shape, doc_embeddings.shape)
 
 similarities = query_embeddings @ doc_embeddings.T
 print(similarities)
-# tensor([[0.7759],
-#         [0.3419]])
+# tensor([[0.6835],
+#         [0.3982]])
 ```
 
-Note the small differences compared to the full 768-dimensional similarities.
+Note the small differences compared to the full 1024-dimensional similarities.
 
 </details>
 
@@ -3116,7 +3116,7 @@ const doc_embeddings = await extractor([
 
 // Compute similarity scores
 const similarities = await matmul(query_embeddings, doc_embeddings.transpose(1, 0));
-console.log(similarities.tolist()); // [[0.721383273601532], [0.3259955644607544]]
+console.log(similarities.tolist());
 ```
 
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "lightonai/modernbert-embed-large-unsupervised-lowerlr",
+  "_name_or_path": "lightonai/modernbert-embed-large",
   "architectures": [
     "ModernBertModel"
   ],

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.0.dev0",
+    "transformers": "4.48.0.dev0",
+    "pytorch": "2.6.0.dev20241112+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}