cross-encoder/quora-roberta-large

The model was trained using SentenceTransformers Cross-Encoder class . It was trained on the Quora Duplicate Questions dataset . The model will predict a score between 0 and 1 how likely the two given questions are duplicates . It is not suitable to estimate the similarity of questions, e.g. the two questions "How to learn Java" will result in a rahter low score, as these are not duplicates. You can use this model also without sentence_transformers and by just using Transformers AutoModel class. The model can be used like this: Pre-trained models can't be used in the same way. Pre-training models can also be used without sentence,