·
AI & ML interests
Reward models
Organizations
reciprocate/lichess-puzzles-only-counterintuitive
Viewer • Updated • 79.8k • 62
reciprocate/lichess-puzzles-evaluated-1M
Viewer • Updated • 1M • 413
reciprocate/kaggle-lmarena-synth-50k
Viewer • Updated • 50.7k • 13
reciprocate/ultra-annotated-200k
Viewer • Updated • 208k • 13
reciprocate/dpo-objective-v0.2
Viewer • Updated • 384 • 7
reciprocate/tinygsm_interpreter_1M
Viewer • Updated • 1M • 105
Viewer • Updated • 541 • 3
reciprocate/dpo_mix-zero-math-untoxic
Viewer • Updated • 6.91k • 10
reciprocate/dpo_mix-7k_untoxic
Viewer • Updated • 7.29k • 5
• 2
reciprocate/tinygsm_mixtral_12M
Viewer • Updated • 12M • 138
• 1
reciprocate/dpo_ultra-capybara-code_filtered-best
Viewer • Updated • 35.2k • 15
• 1
Viewer • Updated • 6.17k • 15
• 2
reciprocate/dpo_ultra-capybara_filtered-best
Viewer • Updated • 25.6k • 21
reciprocate/tinygsm_mixtral_up_dedup
Viewer • Updated • 1.68M • 94
reciprocate/ultrafeedback_orca_math_cleaned_high_dpo
Viewer • Updated • 48.3k • 16
• 2
reciprocate/ultrafeedback_cleaned_high_dpo
Viewer • Updated • 40k • 13
• 2
reciprocate/ultrafeedback_orca_math_dpo
Viewer • Updated • 73.8k • 23
• 2
reciprocate/ultrafeedback_cleaned_v2_dpo
Viewer • Updated • 58.6k • 22
• 1
reciprocate/math_dpo_pairs
Viewer • Updated • 4.38k • 29
• 5
reciprocate/pku_safer_dpo_pairs
Viewer • Updated • 51.8k • 36
reciprocate/pku_better_dpo_pairs
Viewer • Updated • 330k • 20
reciprocate/orca_dpo_pairs
Viewer • Updated • 14.8k • 32
Viewer • Updated • 1k • 20
reciprocate/gsm8k-test_critiques
Viewer • Updated • 753 • 35
• 2
reciprocate/gsm8k_train_pairwise
Viewer • Updated • 7.04k • 36
• 4
reciprocate/gsm8k_pairwise
Viewer • Updated • 128 • 28
• 2
Viewer • Updated • 13k • 28
Viewer • Updated • 10.5k • 115
• 1
Viewer • Updated • 2.37k • 23
reciprocate/vicuna-fair-eval_format-oa
Viewer • Updated • 66 • 20