News for hackers. Stuff that matters.
Re:Introduction to Vector Similarity Search by og_kalu on Wednesday July 12, 2023 @06:19PM (#36702448)
Instead of fine-tuning, you might try out the Instructor series from here. https://instructor-embedding.github.io/ https://huggingface.co/spaces/mteb/leaderboard

Open source and the way it works is that you give an instruction on the type of task or even domain you want the embedding to be tailored to and embeddings change depending on the instructions.

Re:Introduction to Vector Similarity Search by david_shi on Tuesday July 18, 2023 @02:38AM (#36768690)
Instructor performs very well but is still limited to its training corpus. For niche domains, fine-tuning can be helpful in improving performance.