News for hackers. Stuff that matters.
Re:Embeddings: What they are and why they matter by eldenring on Wednesday October 25, 2023 @04:54AM (#38010728)
Fine-tuning an entire language model to solve this problem is like using a sledgehammer on a nail. We have had tools for this for years, for example just label some data and train an SVM on your embedding space for classification.
Re:Embeddings: What they are and why they matter by layoric on Wednesday October 25, 2023 @06:10AM (#38011190)
From my understanding, embedding models are just one layer of a modern LLM that do the similarity part as described in the post. The translation of representing content as a part of a common vocabulary in a vector. My understanding is that embedding models can be fine tuned in isolation to relate a vocabulary entries to each other, so fine tuning a whole LLM is not required, and the required compute resources would be far smaller.