nreimers commited on
Commit
08a5ca3
1 Parent(s): c684b7f

Add new SentenceTransformer model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false
7
+ }
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ - transformers
8
+ - transformers
9
+ - transformers
10
+ - transformers
11
+ - transformers
12
+ - transformers
13
+ - transformers
14
+ - transformers
15
+ - transformers
16
+ - transformers
17
+ ---
18
+
19
+ # sentence-transformers/bert-base-wikipedia-sections-mean-tokens
20
+
21
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
22
+
23
+
24
+
25
+ ## Usage (Sentence-Transformers)
26
+
27
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
28
+
29
+ ```
30
+ pip install -U sentence-transformers
31
+ ```
32
+
33
+ Then you can use the model like this:
34
+
35
+ ```python
36
+ from sentence_transformers import SentenceTransformer
37
+ sentences = ["This is an example sentence", "Each sentence is converted"]
38
+
39
+ model = SentenceTransformer('sentence-transformers/bert-base-wikipedia-sections-mean-tokens')
40
+ embeddings = model.encode(sentences)
41
+ print(embeddings)
42
+ ```
43
+
44
+
45
+
46
+ ## Usage (HuggingFace Transformers)
47
+ Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
48
+
49
+ ```python
50
+ from transformers import AutoTokenizer, AutoModel
51
+ import torch
52
+
53
+
54
+ #Mean Pooling - Take attention mask into account for correct averaging
55
+ def mean_pooling(model_output, attention_mask):
56
+ token_embeddings = model_output[0] #First element of model_output contains all token embeddings
57
+ input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
58
+ return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
59
+
60
+
61
+ # Sentences we want sentence embeddings for
62
+ sentences = ['This is an example sentence', 'Each sentence is converted']
63
+
64
+ # Load model from HuggingFace Hub
65
+ tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-base-wikipedia-sections-mean-tokens')
66
+ model = AutoModel.from_pretrained('sentence-transformers/bert-base-wikipedia-sections-mean-tokens')
67
+
68
+ # Tokenize sentences
69
+ encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
70
+
71
+ # Compute token embeddings
72
+ with torch.no_grad():
73
+ model_output = model(**encoded_input)
74
+
75
+ # Perform pooling. In this case, max pooling.
76
+ sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
77
+
78
+ print("Sentence embeddings:")
79
+ print(sentence_embeddings)
80
+ ```
81
+
82
+
83
+
84
+ ## Evaluation Results
85
+
86
+
87
+
88
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-base-wikipedia-sections-mean-tokens)
89
+
90
+
91
+
92
+ ## Full Model Architecture
93
+ ```
94
+ SentenceTransformer(
95
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
96
+ (1): Pooling({'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})
97
+ )
98
+ ```
99
+
100
+ ## Citing & Authors
101
+
102
+ This model was trained by [sentence-transformers](https://www.sbert.net/).
103
+
104
+ If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
105
+ ```bibtex
106
+ @inproceedings{reimers-2019-sentence-bert,
107
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
108
+ author = "Reimers, Nils and Gurevych, Iryna",
109
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
110
+ month = "11",
111
+ year = "2019",
112
+ publisher = "Association for Computational Linguistics",
113
+ url = "http://arxiv.org/abs/1908.10084",
114
+ }
115
+ ```
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "old_models/bert-base-wikipedia-sections-mean-tokens/0_BERT",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "transformers_version": "4.7.0",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.7.0",
5
+ "pytorch": "1.9.0+cu102"
6
+ }
7
+ }
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79ff0e4558d3b5a4fcd3e085eb745ba22963edcaac48eb2ee27956994d9f37b
3
+ size 438007537
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 128,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "old_models/bert-base-wikipedia-sections-mean-tokens/0_BERT/special_tokens_map.json", "name_or_path": "old_models/bert-base-wikipedia-sections-mean-tokens/0_BERT", "do_basic_tokenize": true, "never_split": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff