Tag: PEFT
Benchmark Transfer After Fine-Tuning: How LLMs Generalize Across Tasks
Explore how LLMs maintain general intelligence after fine-tuning. Learn about benchmark transfer, catastrophic forgetting, and PEFT strategies like LoRA to balance specialization and generalization.
Read More
Prompt-Tuning vs Prefix-Tuning: Lightweight Techniques for LLM Control
Prompt tuning and prefix tuning let you adapt large language models with minimal training. Learn how they differ, when to use each, and why neither can replace full fine-tuning for complex tasks.
Read More