adapter

Definition

A small piece of extra machinery bolted onto a model that can be trained while the original weights stay frozen.

A parameter-efficient module inserted into a pretrained model, often a small MLP or low-rank update, trained while the base remains frozen.

Also called: adapters

Mentioned in 5 episodes

1. 060
   When Splitting One Model Across Three Agents Doubles Its Accuracy
2. 040
   Two Frozen Models Learn to Whisper: Coupling Through Hidden States
3. 026
   What RL Actually Does to Language Models, at the Token Level
4. 025
   The Missing Gradient Term That Predicts Sycophancy in RLHF
5. 004
   The Sycophancy Circuit That Survives Alignment Training

Related concepts