Commit
·
a5f65b1
1
Parent(s):
413f9fd
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,121 @@
|
|
1 |
---
|
|
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
pipeline_tag: sentence-similarity
|
3 |
license: apache-2.0
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- feature-extraction
|
7 |
+
- sentence-similarity
|
8 |
+
- transformers
|
9 |
+
datasets:
|
10 |
+
- flax-sentence-embeddings/stackexchange_xml
|
11 |
+
- s2orc
|
12 |
+
- ms_marco
|
13 |
+
- wiki_atomic_edits
|
14 |
+
- snli
|
15 |
+
- multi_nli
|
16 |
+
- embedding-data/altlex
|
17 |
+
- embedding-data/simple-wiki
|
18 |
+
- embedding-data/flickr30k-captions
|
19 |
+
- embedding-data/coco_captions
|
20 |
+
- embedding-data/sentence-compression
|
21 |
+
- embedding-data/QQP
|
22 |
+
- yahoo_answers_topics
|
23 |
---
|
24 |
+
|
25 |
+
# sentence-transformers/paraphrase-MiniLM-L3-v2
|
26 |
+
|
27 |
+
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.
|
28 |
+
|
29 |
+
|
30 |
+
|
31 |
+
## Usage (Sentence-Transformers)
|
32 |
+
|
33 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
34 |
+
|
35 |
+
```
|
36 |
+
pip install -U sentence-transformers
|
37 |
+
```
|
38 |
+
|
39 |
+
Then you can use the model like this:
|
40 |
+
|
41 |
+
```python
|
42 |
+
from sentence_transformers import SentenceTransformer
|
43 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
44 |
+
|
45 |
+
model = SentenceTransformer('sentence-transformers/paraphrase-MiniLM-L3-v2')
|
46 |
+
embeddings = model.encode(sentences)
|
47 |
+
print(embeddings)
|
48 |
+
```
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
## Usage (HuggingFace Transformers)
|
53 |
+
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.
|
54 |
+
|
55 |
+
```python
|
56 |
+
from transformers import AutoTokenizer, AutoModel
|
57 |
+
import torch
|
58 |
+
|
59 |
+
|
60 |
+
#Mean Pooling - Take attention mask into account for correct averaging
|
61 |
+
def mean_pooling(model_output, attention_mask):
|
62 |
+
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
|
63 |
+
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
|
64 |
+
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
|
65 |
+
|
66 |
+
|
67 |
+
# Sentences we want sentence embeddings for
|
68 |
+
sentences = ['This is an example sentence', 'Each sentence is converted']
|
69 |
+
|
70 |
+
# Load model from HuggingFace Hub
|
71 |
+
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-MiniLM-L3-v2')
|
72 |
+
model = AutoModel.from_pretrained('sentence-transformers/paraphrase-MiniLM-L3-v2')
|
73 |
+
|
74 |
+
# Tokenize sentences
|
75 |
+
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
76 |
+
|
77 |
+
# Compute token embeddings
|
78 |
+
with torch.no_grad():
|
79 |
+
model_output = model(**encoded_input)
|
80 |
+
|
81 |
+
# Perform pooling. In this case, max pooling.
|
82 |
+
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
|
83 |
+
|
84 |
+
print("Sentence embeddings:")
|
85 |
+
print(sentence_embeddings)
|
86 |
+
```
|
87 |
+
|
88 |
+
|
89 |
+
|
90 |
+
## Evaluation Results
|
91 |
+
|
92 |
+
|
93 |
+
|
94 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/paraphrase-MiniLM-L3-v2)
|
95 |
+
|
96 |
+
|
97 |
+
|
98 |
+
## Full Model Architecture
|
99 |
+
```
|
100 |
+
SentenceTransformer(
|
101 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
102 |
+
(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})
|
103 |
+
)
|
104 |
+
```
|
105 |
+
|
106 |
+
## Citing & Authors
|
107 |
+
|
108 |
+
This model was trained by [sentence-transformers](https://www.sbert.net/).
|
109 |
+
|
110 |
+
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):
|
111 |
+
```bibtex
|
112 |
+
@inproceedings{reimers-2019-sentence-bert,
|
113 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
114 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
115 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
116 |
+
month = "11",
|
117 |
+
year = "2019",
|
118 |
+
publisher = "Association for Computational Linguistics",
|
119 |
+
url = "http://arxiv.org/abs/1908.10084",
|
120 |
+
}
|
121 |
+
```
|