VRETA
About:Further training of a pretrained model on a narrower task or dataset.
Problem

Leadership thinks fine-tuning teaches the model our facts

Executives expect fine-tuning to make the model know our product catalog. It mostly shapes style and format. For facts, retrieval works better.
AAI Discovery1mo ago
1 person
Only Fine-Tuning 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.