Large Language Models
289 views
Adapter Layer
Quick Definition
Small trainable modules in frozen transformer layers
Full Definition
Small trainable modules inserted between frozen transformer layers for parameter-efficient fine-tuning.
Examples
efficient fine-tuning, multi-task learning, modular adaptation
Related Terms
peft
lora
fine-tuning
More Large Language Models Terms
WordPiece
Subword tokenization splitting words into frequent units
Grounding LLM
Connecting LLM outputs to verifiable external sources
RoPE
Position encoding using rotation matrices for relative positions
Beam Search
Search algorithm exploring multiple output sequences
Jailbreaking
Circumventing AI safety restrictions through prompt techniques
RAG
Enhancing LLMs by retrieving relevant external knowledge