reciprocate/kaggle-lmarena-synth-50k
Viewer • Updated • 50.7k • 26
Max PRO
reciprocate
AI & ML interests
Reward models
Organizations
reciprocate/ultra-annotated-200k
Viewer • Updated • 208k • 173
reciprocate/dpo-objective-v0.2
Viewer • Updated • 384 • 12
reciprocate/tinygsm_interpreter_1M
Viewer • Updated • 1M • 8
reciprocate/dpo_untoxic
Viewer • Updated • 541 • 49
reciprocate/dpo_mix-zero-math-untoxic
Viewer • Updated • 6.91k • 22
reciprocate/dpo_mix-7k_untoxic
Viewer • Updated • 7.29k • 42 • 2
reciprocate/tinygsm_mixtral_12M
Viewer • Updated • 12M • 37 • 1
reciprocate/dpo_ultra-capybara-code_filtered-best
Viewer • Updated • 35.2k • 102 • 1
reciprocate/tinygsm_dpo
Viewer • Updated • 6.17k • 32 • 2
reciprocate/dpo_ultra-capybara_filtered-best
Viewer • Updated • 25.6k • 6
reciprocate/tinygsm_mixtral_up_dedup
Viewer • Updated • 1.68M • 9
reciprocate/ultrafeedback_orca_math_cleaned_high_dpo
Viewer • Updated • 48.3k • 12 • 2
reciprocate/ultrafeedback_cleaned_high_dpo
Viewer • Updated • 40k • 57 • 2
reciprocate/ultrafeedback_orca_math_dpo
Viewer • Updated • 73.8k • 26 • 2
reciprocate/ultrafeedback_cleaned_v2_dpo
Viewer • Updated • 58.6k • 125 • 1
reciprocate/math_dpo_pairs
Viewer • Updated • 4.38k • 147 • 5
reciprocate/pku_safer_dpo_pairs
Viewer • Updated • 51.8k • 31
reciprocate/pku_better_dpo_pairs
Viewer • Updated • 330k • 13
reciprocate/orca_dpo_pairs
Viewer • Updated • 14.8k • 26
reciprocate/number-pairs
Viewer • Updated • 1k • 12
reciprocate/gsm8k-test_critiques
Viewer • Updated • 753 • 47 • 2
reciprocate/gsm8k_train_pairwise
Viewer • Updated • 7.04k • 42 • 4
reciprocate/gsm8k_pairwise
Viewer • Updated • 128 • 35 • 2
reciprocate/megasynth
Viewer • Updated • 13k • 10
reciprocate/alpaca-eval
Viewer • Updated • 10.5k • 12 • 1
reciprocate/synth_clean
Viewer • Updated • 2.37k • 9
reciprocate/vicuna-fair-eval_format-oa
Viewer • Updated • 66 • 10
reciprocate/vicuna-fair-eval
Viewer • Updated • 66 • 27
reciprocate/vicuna_fair_eval_dataset
Viewer • Updated • 66 • 7