nreimers commited on
Commit
c20c4ef
1 Parent(s): ff7f8c6

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 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - transformers
18
+ - transformers
19
+ - transformers
20
+ - transformers
21
+ - transformers
22
+ - transformers
23
+ - transformers
24
+ - transformers
25
+ - transformers
26
+ - transformers
27
+ - transformers
28
+ - transformers
29
+ ---
30
+
31
+ # sentence-transformers/distilbert-base-nli-mean-tokens
32
+
33
+ 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.
34
+
35
+
36
+
37
+ ## Usage (Sentence-Transformers)
38
+
39
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
40
+
41
+ ```
42
+ pip install -U sentence-transformers
43
+ ```
44
+
45
+ Then you can use the model like this:
46
+
47
+ ```python
48
+ from sentence_transformers import SentenceTransformer
49
+ sentences = ["This is an example sentence", "Each sentence is converted"]
50
+
51
+ model = SentenceTransformer('sentence-transformers/distilbert-base-nli-mean-tokens')
52
+ embeddings = model.encode(sentences)
53
+ print(embeddings)
54
+ ```
55
+
56
+
57
+
58
+ ## Usage (HuggingFace Transformers)
59
+ 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.
60
+
61
+ ```python
62
+ from transformers import AutoTokenizer, AutoModel
63
+ import torch
64
+
65
+
66
+ #Mean Pooling - Take attention mask into account for correct averaging
67
+ def mean_pooling(model_output, attention_mask):
68
+ token_embeddings = model_output[0] #First element of model_output contains all token embeddings
69
+ input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
70
+ return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
71
+
72
+
73
+ # Sentences we want sentence embeddings for
74
+ sentences = ['This is an example sentence', 'Each sentence is converted']
75
+
76
+ # Load model from HuggingFace Hub
77
+ tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilbert-base-nli-mean-tokens')
78
+ model = AutoModel.from_pretrained('sentence-transformers/distilbert-base-nli-mean-tokens')
79
+
80
+ # Tokenize sentences
81
+ encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
82
+
83
+ # Compute token embeddings
84
+ with torch.no_grad():
85
+ model_output = model(**encoded_input)
86
+
87
+ # Perform pooling. In this case, max pooling.
88
+ sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
89
+
90
+ print("Sentence embeddings:")
91
+ print(sentence_embeddings)
92
+ ```
93
+
94
+
95
+
96
+ ## Evaluation Results
97
+
98
+
99
+
100
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distilbert-base-nli-mean-tokens)
101
+
102
+
103
+
104
+ ## Full Model Architecture
105
+ ```
106
+ SentenceTransformer(
107
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
108
+ (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})
109
+ )
110
+ ```
111
+
112
+ ## Citing & Authors
113
+
114
+ This model was trained by [sentence-transformers](https://www.sbert.net/).
115
+
116
+ 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):
117
+ ```bibtex
118
+ @inproceedings{reimers-2019-sentence-bert,
119
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
120
+ author = "Reimers, Nils and Gurevych, Iryna",
121
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
122
+ month = "11",
123
+ year = "2019",
124
+ publisher = "Association for Computational Linguistics",
125
+ url = "http://arxiv.org/abs/1908.10084",
126
+ }
127
+ ```
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "old_models/distilbert-base-nli-mean-tokens/0_Transformer",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "transformers_version": "4.7.0",
22
+ "vocab_size": 30522
23
+ }
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 sha256:5d4551851fc88a3b212a38316b255c3c160b768c167a982e9570fd2e482fe10e
3
+ size 265486777
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, "model_max_length": 512, "special_tokens_map_file": "old_models/distilbert-base-nli-mean-tokens/0_Transformer/special_tokens_map.json", "name_or_path": "old_models/distilbert-base-nli-mean-tokens/0_Transformer", "do_basic_tokenize": true, "never_split": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff