Integrate with Sentence Transformers (#7)

- Add Sentence Transformers configuration files (7c8af9e29d638aa324e20a96b7258267f9ee1c1c)
- Update the snippet slightly (d42246521432af1e55af2f7a4785d79755b32ba7)
- Add output if you have the correct transformers version (aca0f8a967302f7f6989444130bef6ef27cca0e9)

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 4096,
+    "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

@@ -3,13 +3,15 @@ license: other
 license_name: customized-nscl-v1
 license_link: LICENSE
 tags:
+  - transformers
   - text
   - sentence-similarity
   - feature-extraction
   - mteb
+  - mmteb
 language:
   - multilingual
-library_name: transformers
+library_name: sentence-transformers
 ---
 
 # llama-embed-nemotron-8b
@@ -128,6 +130,43 @@ pip install transformers==4.51.0
 pip install flash-attn==2.6.3
 ```
 
+You can use either Sentence Transformers like here:
+
+```bash
+pip install sentence-transformers
+```
+
+```python
+from sentence_transformers import SentenceTransformer
+
+attn_implementation = "eager"  # Or "flash_attention_2"
+model = SentenceTransformer(
+    "nvidia/llama-embed-nemotron-8b",
+    trust_remote_code=True,
+    model_kwargs={"attn_implementation": attn_implementation, "torch_dtype": "float16"},
+    tokenizer_kwargs={"padding_side": "left"},
+)
+
+queries = [
+    "How do neural networks learn patterns from examples?"
+]
+documents = [
+    "Deep learning models adjust their weights through backpropagation, using gradient descent to minimize error on training data and improve predictions over time.",
+    "Market prices are determined by the relationship between how much people want to buy a product and how much is available for sale, with scarcity driving prices up and abundance driving them down.",
+]
+
+# NOTE: encode_query uses the "query" prompt automatically
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+
+scores = (query_embeddings @ document_embeddings.T)
+
+print(scores.tolist())
+# [[0.37646484375, 0.057891845703125]]
+```
+
+Or using Hugging Face Transformers like here:
+
 ```python
 import torch
 import torch.nn.functional as F

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.57.1",
+    "pytorch": "2.8.0+cu128"
+  },
+  "prompts": {
+    "query": "Instruct: Given a question, retrieve passages that answer the question\nQuery: ",
+    "document": ""
+  },
+  "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": 131072,
+    "do_lower_case": false
+}