README.md
3.4 KB · 100 lines · markdown Raw
1 ---
2 license: apache-2.0
3 library_name: sentence-transformers
4 tags:
5 - sentence-transformers
6 - feature-extraction
7 - sentence-similarity
8 - transformers
9 pipeline_tag: sentence-similarity
10 ---
11
12 # sentence-transformers/paraphrase-MiniLM-L6-v2
13
14 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
15
16
17
18 ## Usage (Sentence-Transformers)
19
20 Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
21
22 ```
23 pip install -U sentence-transformers
24 ```
25
26 Then you can use the model like this:
27
28 ```python
29 from sentence_transformers import SentenceTransformer
30 sentences = ["This is an example sentence", "Each sentence is converted"]
31
32 model = SentenceTransformer('sentence-transformers/paraphrase-MiniLM-L6-v2')
33 embeddings = model.encode(sentences)
34 print(embeddings)
35 ```
36
37
38
39 ## Usage (HuggingFace Transformers)
40 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.
41
42 ```python
43 from transformers import AutoTokenizer, AutoModel
44 import torch
45
46
47 #Mean Pooling - Take attention mask into account for correct averaging
48 def mean_pooling(model_output, attention_mask):
49 token_embeddings = model_output[0] #First element of model_output contains all token embeddings
50 input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
51 return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
52
53
54 # Sentences we want sentence embeddings for
55 sentences = ['This is an example sentence', 'Each sentence is converted']
56
57 # Load model from HuggingFace Hub
58 tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')
59 model = AutoModel.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')
60
61 # Tokenize sentences
62 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
63
64 # Compute token embeddings
65 with torch.no_grad():
66 model_output = model(**encoded_input)
67
68 # Perform pooling. In this case, max pooling.
69 sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
70
71 print("Sentence embeddings:")
72 print(sentence_embeddings)
73 ```
74
75
76
77 ## Full Model Architecture
78 ```
79 SentenceTransformer(
80 (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
81 (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
82 )
83 ```
84
85 ## Citing & Authors
86
87 This model was trained by [sentence-transformers](https://www.sbert.net/).
88
89 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):
90 ```bibtex
91 @inproceedings{reimers-2019-sentence-bert,
92 title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
93 author = "Reimers, Nils and Gurevych, Iryna",
94 booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
95 month = "11",
96 year = "2019",
97 publisher = "Association for Computational Linguistics",
98 url = "http://arxiv.org/abs/1908.10084",
99 }
100 ```