New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fine-tune embedding model (by using adapters) #84

Open

rchan26 opened this issue Sep 13, 2023 · 0 comments

Labels

enhancement idea

Collaborator

rchan26 commented Sep 13, 2023

Fine-tuning embeddings typically improves RAG performance. llama-index now has functionality to allow you to do this by adding an adapter on top of the embeddings and fine-tuning those. See this notebook: https://gpt-index.readthedocs.io/en/latest/examples/finetuning/embeddings/finetune_embedding_adapter.html

It also seems to have functionality to generate Q&A pairs. Something to investigate.

rchan26 added enhancement idea labels

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment