search

UKPLab / sentence-transformers

Multilingual Sentence & Image Embeddings with BERT
https://www.SBERT.net
Apache License 2.0
14.33k stars 2.39k forks source link

clip-ViT-B-32-multilingual-v1 benchmark #1106

Open Siegi96 opened 2 years ago

Siegi96 commented 2 years ago

Even the model is able to handle images, performance/benchmark comparison on text datasets with other text2vec models would be interesting.

nreimers commented 2 years ago

I only evaluated the English CLIP model. It does not perform that well for general embeddings task.

Evaluated on 14 tasks, it achieves an avg. performance of 57.5. The paraphrase-v2 models are at 65-67 on the same tasks.