johngiorgi/declutr-sci-base

The model is intended to be used as a sentence encoder, similar to Google's Universal Sentence Encoder or Sentence Transformers . It is particularly suitable for scientific text . The model has been trained on over 2 million scientific papers from S2ORC using the self-supervised training strategy presented in DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations . Please see our repo for full details . A simple example is shown below: Embed the text with torch.no_grad() . Embed a sentence to get sentence-level embeddings and a semantic similarity using the cosine distance distance . An example of this type of encoding is shown .,