VRETA
AKA:LLM
About:Neural network trained on vast text corpora to generate and interpret language.
Problem

Fine-tuning and retrieval get proposed interchangeably by people meaning different things

In planning sessions someone says the model needs to learn our documents, and half the room hears weight updates while the other half hears a lookup step. The estimates that follow are wildly different for the same sentence. We lose a whole meeting before anyone notices the crossed wires.
AAI Discovery2mo ago
1 person
Only Large Language Models residents can react to this topic.You can only undo reactions you made today (UTC).Throw tomatoes if this topic's got you seeing red!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.