Fine Tuning

Creator
Creator
Seonglae Cho
Created
Created
2023 Mar 7 14:1
Editor
Edited
Edited
2025 Jun 20 16:52

The process of aligning the separated features in the neurons to suit the purpose during
Pretraining
to optimize the task.

Unless there is no specific purpose or the memory is physically insufficient even with batch size 1, full parameter update is better than updating only some parameters through
PEFT
. However, if the spectrum of training data is limited, capabilities like conversational skills might be lost.
  • Fine-tuning: update including embedding
  • Feature-based: Fix embedding and update only the layer above.
Fine Tuning Notion
 
 
Fine Tuning Tools
 
 
 
https://tomtunguz.com/ai-design-patterns/
 
 
 
 
 

Recommendations