·
AI & ML interests
LLMs, RLHF
Organizations
Viewer
• Updated • 21k • 20
Viewer
• Updated • 21k • 7
Viewer
• Updated • 21k • 16
Viewer
• Updated • 21k • 8
ftajwar/knights_and_knaves_fraction_reward
Viewer
• Updated • 21k • 25
ftajwar/knights_and_knaves
Viewer
• Updated • 11k • 11
ftajwar/evaluation_bitwise_arithmetic-2
Viewer
• Updated • 110 • 4
ftajwar/training_bitwise_arithmetic-2
Viewer
• Updated • 20k • 6
ftajwar/evaluation_family_relationships_5
Viewer
• Updated • 100 • 9
ftajwar/evaluation_family_relationships_4
Viewer
• Updated • 100 • 9
ftajwar/training_family_relationships_5
Viewer
• Updated • 20k • 10
ftajwar/training_family_relationships_4
Viewer
• Updated • 20k • 13
ftajwar/evaluation_bitwise_arithmetic-4
Viewer
• Updated • 110 • 4
ftajwar/evaluation_bitwise_arithmetic-3
Viewer
• Updated • 110 • 15
ftajwar/training_bitwise_arithmetic-4
Viewer
• Updated • 20k • 52
ftajwar/training_bitwise_arithmetic-3
Viewer
• Updated • 20k • 5
ftajwar/evaluation_knight-knave-9
Viewer
• Updated • 100 • 5
ftajwar/evaluation_knight-knave-7
Viewer
• Updated • 100 • 5
ftajwar/evaluation_knight-knave-2
Viewer
• Updated • 100 • 4
ftajwar/training_knight-knave-7
Viewer
• Updated • 20k • 4
ftajwar/training_knight-knave-9
Viewer
• Updated • 20k • 3
ftajwar/training_knight-knave-2
Viewer
• Updated • 20k • 4
ftajwar/deduplicated_dapo_dataset
Viewer
• Updated • 17.4k • 93
• 1
ftajwar/dapo_easy_one_third_sorted_by_frequency_of_majority_answer
Viewer
• Updated • 5.8k • 46
• 1
ftajwar/dapo_easy_one_third_sorted_by_pass_rate
Viewer
• Updated • 5.8k • 24
Viewer
• Updated • 273 • 21
ftajwar/paprika_SFT_dataset
Viewer
• Updated • 17.2k • 4
• 3
ftajwar/paprika_preference_dataset
Viewer
• Updated • 5.26k • 15
• 1