This is the code repo for paper CREAM: Consistency Regularized Self-Rewarding Language Models accepted to ICLR 2025. CREAM extends the Self-Rewarding Language Model (SRLM) to small models (e.g., ...
It also includes automatic tuning, caching, and a Pythonic interface for ease of use. Tilus is pronounced as tie-lus, /ˈtaɪləs/. Tilus supports Ampere architecture, and we are actively working on the ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results