D-RLAIF - a Dening Collection

Dening 's Collections

D-RLAIF

updated Apr 7, 2025

openai/summarize_from_feedback

Viewer • Updated Jan 3, 2023 • 194k • 2.34k • 220
trl-internal-testing/tldr-preference-sft-trl-style

Viewer • Updated Aug 20, 2024 • 130k • 180 • 3