navteca/quora-roberta-base

The model was trained on the Quora Duplicate Questions dataset . It will predict a score between 0 and 1: How likely the two given questions are duplicates . The model 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. The model uses roberta-base.iopio-base .iopio is based on the data from SentenceTransformers Cross-Encoder class Sentence-Transformer class . It was trained using the CrossEncoder Cross Encoder to detect duplicates in the question-based questions . The score is between,