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

Fine-tuning and training from scratch get used interchangeably

In our planning meetings, people say we will train our own model when they mean fine-tuning an existing one. The budgets and timelines are very different. The vocabulary leads to wrong estimates.
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.