Carft Contrastive Reinforced Finetuning

Enhance LLM reasoning by combining contrastive learning on reasoning representations with reinforced fine-tuning, leveraging both annotated chains and unsupervised signals.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit f69a6413e9

Frequently asked questions

npx get-skill add adu2021/carft-contrastive-reinforced-finetuning