saurabh18cs
Honored Contributor II

Hi @Suheb 

Summary Table:

Method What’s Tuned Speed/Cost Flexibility Use Case

Full Fine-TuningAll model weightsSlow/HighMaximumCustom tasks, large data
LoRASmall adapter layersFast/LowHighEfficient adaptation
p-tuningPrompt embeddingsFastest/LowLimitedPrompt-based tasks