jgrosjean-mathesis
/

sentence-swissbert

Sentence Similarity

Inference Endpoints

Model card Files Files and versions Community

jgrosjean commited on Feb 26

Commit

e2f0db1

•

1 Parent(s): d4f0c20

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ language:
 The [SwissBERT](https://huggingface.co/ZurichNLP/swissbert) model was finetuned via self-supervised [SimCSE](http://dx.doi.org/10.18653/v1/2021.emnlp-main.552) (Gao et al., EMNLP 2021) for sentence embeddings, using ~1.5 million Swiss news articles from up to 2023 retireved via [Swissdox@LiRI](https://t.uzh.ch/1hI). Following the [Sentence Transformers](https://huggingface.co/sentence-transformers) approach (Reimers and Gurevych,
 2019), the average of the last hidden states (pooler_type=avg) is used as sentence representation.
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6564ab8d113e2baa55830af0/8oGfxvuzZnDwh2e71HgKr.png)
 ## Model Details

 The [SwissBERT](https://huggingface.co/ZurichNLP/swissbert) model was finetuned via self-supervised [SimCSE](http://dx.doi.org/10.18653/v1/2021.emnlp-main.552) (Gao et al., EMNLP 2021) for sentence embeddings, using ~1.5 million Swiss news articles from up to 2023 retireved via [Swissdox@LiRI](https://t.uzh.ch/1hI). Following the [Sentence Transformers](https://huggingface.co/sentence-transformers) approach (Reimers and Gurevych,
 2019), the average of the last hidden states (pooler_type=avg) is used as sentence representation.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6564ab8d113e2baa55830af0/owPx_nx0evzbl8aGm-UzQ.png)
 ## Model Details