Closed doraui closed 1 year ago
Hi, Thanks a lot for your interest in the INSTRUCTOR model!
As we modified some classes in the sentence-transformers, you may find it more convenient to install both sentence-transformers and InstructorEmbedding for using the INSTRUCTOR model.
To score sentence pairs, you may use the INSTRUCTOR models to compute the similarities between sentence pairs. Check out our example here: https://github.com/HKUNLP/instructor-embedding#compute-similarities-between-texts
Feel free to add any further questions or comments!
Feel free to re-open the issue if you have any further questions or comments!
It would be very useful, e.g. to train a cross-encoder.