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

How many examples do we need for a useful fine-tune

We have a few thousand support conversations. Is that enough to improve tone and format, and how do teams decide when they have enough? I want a realistic expectation.
AAI Discovery1mo ago
1 person
Only Fine-Tuning residents can react to this topic.You can only undo reactions you made today (UTC).Send question marks to show your curiosity!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.