rlaif

There are 7 repositories under rlaif topic.

argilla-io/distilabel
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Language:Python1.4k 13 413108
mengdi-li/awesome-RLAIF
A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)
119 4 14
vicgalle/zero-shot-reward-models
ZYN: Zero-Shot Reward Models with Yes-No Questions
Language:Python33 2 18
holarissun/Prompt-OIRL
code for paper Query-Dependent Prompt Evaluation and Optimization with Offline Inverse Reinforcement Learning
Language:Python26 2 45
zhaochen0110/Timo
Timo: Towards Better Temporal Reasoning for Language Models (COLM 2024)
Language:Python17 1 01
vicgalle/distilled-self-critique
distilled Self-Critique refines the outputs of a LLM with only synthetic data
Language:Jupyter Notebook11 2 00
vicgalle/awesome-rlaif
A curated and updated list of relevant articles and repositories on Reinforcement Learning from AI Feedback (RLAIF)
9 2 00