Different types of embedding used internally inside the tool?
pradeepdev-1995 opened this issue · comments
What are the different types of embeddings such as (sentence transformer embedding, spacy embedding, bert embedding, glove embedding, openai embedding,cohere embedding, huggingface embedding...etc) used internally in instructor-embedding ?
or instructor-embedding use its own embedding?
Please explain what is happening internally.
Hi, Thanks a lot for your interest in the INSTRUCTOR!
Different types of embeddings use different backend models with various architectures and training data, and we have also trained a general model with T5-structure for efficient adaptation in INSTRUCTOR embedding. For details, please refer to our paper: https://arxiv.org/abs/2212.09741
Feel free to re-open the issue if your have any further questions or comments!