Hugging Face's logo

cambridgeltl
/
trans-encoder-bi-simcse-roberta-large

Feature Extraction
Transformers
PyTorch
roberta
text-embeddings-inference
Model card Files
xet
 Community
1
fl399 commited on
Commit
a1ac978
·
1 Parent(s): 1cdd3d9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -4,6 +4,7 @@ language: en
4
  tags:
5
  - sentence-embeddings
6
  - sentence-similarity
 
7
 
8
  ### cambridgeltl/trans-encoder-bi-simcse-roberta-large
9
  An unsupervised sentence encoder (bi-encoder) proposed by [Liu et al. (2021)](https://arxiv.org/pdf/2109.13059.pdf). The model is trained with unlabelled sentence pairs sampled from STS2012-2016, STS-b, and SICK-R, using [princeton-nlp/unsup-simcse-roberta-large](https://huggingface.co/princeton-nlp/unsup-simcse-roberta-large) as the base model. Please use `[CLS]` (before pooler) as the representation of the input.
 
4
  tags:
5
  - sentence-embeddings
6
  - sentence-similarity
7
+ - dual-encoder
8
 
9
  ### cambridgeltl/trans-encoder-bi-simcse-roberta-large
10
  An unsupervised sentence encoder (bi-encoder) proposed by [Liu et al. (2021)](https://arxiv.org/pdf/2109.13059.pdf). The model is trained with unlabelled sentence pairs sampled from STS2012-2016, STS-b, and SICK-R, using [princeton-nlp/unsup-simcse-roberta-large](https://huggingface.co/princeton-nlp/unsup-simcse-roberta-large) as the base model. Please use `[CLS]` (before pooler) as the representation of the input.