Add proper Sentence Transformers integration (#1)

- Add ST-specific configuration files with model.save() (7260df65f5d871b2743995da4cc2342b8f954844)
- Also add a transformers tag (c58c14f76620c82c5e8e307c91e8edda2eda2a72)
- Following SFR-Embedding-Mistral, set max seq length to 4096 (6cf3bfedf3c5c2d24b7730664985cdc11ffbb154)

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 4096,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": true,
+  "include_prompt": true
+}

README.md

@@ -1,6 +1,8 @@
 ---
 tags:
 - mteb
+- sentence-transformers
+- transformers
 model-index:
 - name: Salesforce/SFR-Embedding-2_R
   results:
@@ -2007,8 +2009,7 @@ print(scores.tolist())
 
 ### Sentence Transformers
 ```python
-
-from sentence_transformers import SentenceTransformer, util
+from sentence_transformers import SentenceTransformer
 
 model = SentenceTransformer("Salesforce/SFR-Embedding-2_R")
 
@@ -2028,9 +2029,9 @@ passages = [
 ]
 
 embeddings = model.encode(queries + passages)
-scores = util.cos_sim(embeddings[:2], embeddings[2:]) * 100
+scores = model.similarity(embeddings[:2], embeddings[2:]) * 100
 print(scores.tolist())
-# [[40.132083892822266, 25.032529830932617], [15.006855010986328, 39.93733215332031]]
+# [[40.13203811645508, 25.032546997070312], [15.00684642791748, 39.937339782714844]]
 ```
 
 

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 4096,
+  "do_lower_case": false
+}