thomasbllx/ppo-ltr-run_approxndcg_seed123
Text Ranking • 4B • Updated
PPO Learning to Rank
Reward models and five-level graded explanation-ranking datasets for PPO Learning to Rank experiments.
-
-
thomasbllx/ppo-ltr-run_approxndcg_seed42
Text Ranking • 4B • Updated -
thomasbllx/ppo-ltr-run_approxndcg_seed7
Text Ranking • 4B • Updated -
thomasbllx/ppo-ltr-run_listnet_seed123
Text Ranking • 4B • Updated • 1 -
thomasbllx/ppo-ltr-run_listnet_seed42
Text Ranking • 4B • Updated • 1 -
thomasbllx/ppo-ltr-run_listnet_seed7
Text Ranking • 4B • Updated -
thomasbllx/ppo-ltr-run_mse_seed123
Text Ranking • 4B • Updated • 1 -
thomasbllx/ppo-ltr-run_mse_seed42
Text Ranking • 4B • Updated -
thomasbllx/ppo-ltr-run_mse_seed7
Text Ranking • 4B • Updated -
thomasbllx/ppo-ltr-run_ranknet_seed123
Text Ranking • 4B • Updated -
thomasbllx/ppo-ltr-run_ranknet_seed42
Text Ranking • 4B • Updated -
thomasbllx/ppo-ltr-run_ranknet_seed7
Text Ranking • 4B • Updated -
thomasbllx/ppo-ltr-comprehensive-ranking-dataset
Viewer • Updated • 149k • 19 -
thomasbllx/ppo-ltr-graded-esnli
Viewer • Updated • 16.2k • 18 -
thomasbllx/ppo-ltr-graded-delta-nli
Viewer • Updated • 700 • 17 -
thomasbllx/ppo-ltr-graded-delta-nli-heuristic
Viewer • Updated • 700 • 17 -
thomasbllx/ppo-ltr-graded-delta-nli-llm
Viewer • Updated • 140 • 61 -
thomasbllx/ppo-ltr-graded-delta-nli-overlap
Viewer • Updated • 600 • 18 -
thomasbllx/ppo-ltr-graded-multi-nli-overlap
Viewer • Updated • 700 • 34 -
thomasbllx/ppo-ltr-graded-snli-overlap
Viewer • Updated • 697 • 31