Add files for Sentence Transformers integration

Note: running it with Transformers or anything else still works as usual :)

1_Pooling/config.json

@@ -1,10 +1,9 @@
 {
-    "word_embedding_dimension": 768,
-    "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
-  }
-  
+  "word_embedding_dimension": 768,
+  "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
+}

README.md

@@ -2655,6 +2655,17 @@ Training data to train the models is released in its entirety. For more details,
 
 ## Usage
 
+### Sentence Transformers
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("../nomic-embed-text-v1", trust_remote_code=True)
+sentences = ['What is TSNE?', 'Who is Laurens van der Maaten?']
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+### Transformers
 
 ```python
 import torch
@@ -2669,7 +2680,7 @@ def mean_pooling(model_output, attention_mask):
 sentences = ['What is TSNE?', 'Who is Laurens van der Maaten?']
 
 tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
-model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1-unsupervised', trust_remote_code=True)
+model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True)
 
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
 
@@ -2688,8 +2699,8 @@ The model natively supports scaling of the sequence length past 2048 tokens. To
 + tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192)
 
 
-- model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1-unsupervised', trust_remote_code=True)
-+ model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1-unsupervised', trust_remote_code=True, rotary_scaling_factor=2)
+- model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True)
++ model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True, rotary_scaling_factor=2)
 ```
 
 # Join the Nomic Community

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.4.0.dev0",
+    "transformers": "4.37.2",
+    "pytorch": "2.1.0+cu121"
+  }
+}

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": 8192,
+  "do_lower_case": false
+}

tokenizer_config.json

@@ -45,7 +45,7 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 8192,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,