sentence-transformers (#1)

- feat: sentence transformers (51a9ea9e49d0fe871a0d12e269575b76e4c92711)

1_Pooling/config.json

@@ -0,0 +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
+  }

README.md

@@ -2670,11 +2670,17 @@ For retrieval applications, you should prepend `search_document` for all your do
 
 ### Sentence Transformers
 ```python
+import torch.nn.functional as F
 from sentence_transformers import SentenceTransformer
 
-model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True)
+matryoshka_dim = 512
+
+model = SentenceTransformer(".", trust_remote_code=True)
 sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']
 embeddings = model.encode(sentences)
+embeddings = F.layer_norm(embeddings, normalized_shape=(embeddings.shape[1],))
+embeddings = embeddings[:, :matryoshka_dim]
+embeddings = F.normalize(embeddings, p=2, dim=1)
 print(embeddings)
 ```
 

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
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}