You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Reflector: independent interjection classification via reflection pretrained distillation
labels: experimental, llm, agentic, post-training
train some lightweight model to predict whether or not the next token will be a <reflection> as a mechanism for distilling a reflection behavior into an isolated component that can be used in conjunction with any model.