🍥 em

Max PRO

reciprocate

·

maxreciprocate

AI & ML interests

Reward models

Recent Activity

updated a dataset about 2 hours ago

reciprocate/lichess-puzzles-counterintuitive

published a dataset about 2 hours ago

reciprocate/lichess-puzzles-counterintuitive

updated a dataset about 2 hours ago

reciprocate/lichess-puzzles-evaluated-1M

View all activity

Organizations

reciprocate 's datasets 37

reciprocate/lichess-puzzles-counterintuitive

Viewer • Updated about 2 hours ago • 14k

reciprocate/lichess-puzzles-evaluated-1M

Viewer • Updated about 2 hours ago • 1M

reciprocate/kaggle-lmarena-synth-50k

Viewer • Updated Mar 23, 2025 • 50.7k • 58

reciprocate/ultra-annotated-200k

Viewer • Updated Sep 1, 2024 • 208k • 21

reciprocate/dpo-objective-v0.2

Viewer • Updated May 14, 2024 • 384 • 17

reciprocate/tinygsm_interpreter_1M

Viewer • Updated May 6, 2024 • 1M • 43

reciprocate/dpo_untoxic

Viewer • Updated Apr 7, 2024 • 541 • 30

reciprocate/dpo_mix-zero-math-untoxic

Viewer • Updated Mar 29, 2024 • 6.91k • 12

reciprocate/dpo_mix-7k_untoxic

Viewer • Updated Mar 26, 2024 • 7.29k • 20 • 2

reciprocate/tinygsm_mixtral_12M

Viewer • Updated Mar 24, 2024 • 12M • 357 • 1

reciprocate/dpo_ultra-capybara-code_filtered-best

Viewer • Updated Mar 19, 2024 • 35.2k • 56 • 1

reciprocate/tinygsm_dpo

Viewer • Updated Mar 15, 2024 • 6.17k • 15 • 2

reciprocate/dpo_ultra-capybara_filtered-best

Viewer • Updated Mar 14, 2024 • 25.6k • 9

reciprocate/tinygsm_mixtral_up_dedup

Viewer • Updated Mar 11, 2024 • 1.68M • 8

reciprocate/ultrafeedback_orca_math_cleaned_high_dpo

Viewer • Updated Jan 11, 2024 • 48.3k • 13 • 2

reciprocate/ultrafeedback_cleaned_high_dpo

Viewer • Updated Jan 11, 2024 • 40k • 15 • 2

reciprocate/ultrafeedback_orca_math_dpo

Viewer • Updated Jan 8, 2024 • 73.8k • 17 • 2

reciprocate/ultrafeedback_cleaned_v2_dpo

Viewer • Updated Jan 8, 2024 • 58.6k • 46 • 1

reciprocate/math_dpo_pairs

Viewer • Updated Jan 5, 2024 • 4.38k • 12 • 5

reciprocate/pku_safer_dpo_pairs

Viewer • Updated Jan 3, 2024 • 51.8k • 21

reciprocate/pku_better_dpo_pairs

Viewer • Updated Jan 3, 2024 • 330k • 14

reciprocate/orca_dpo_pairs

Viewer • Updated Jan 3, 2024 • 14.8k • 11

reciprocate/number-pairs

Viewer • Updated Nov 20, 2023 • 1k • 7

reciprocate/gsm8k-test_critiques

Viewer • Updated Sep 15, 2023 • 753 • 9 • 2

reciprocate/gsm8k_train_pairwise

Viewer • Updated Sep 2, 2023 • 7.04k • 8 • 4

reciprocate/gsm8k_pairwise

Viewer • Updated Aug 23, 2023 • 128 • 11 • 2

reciprocate/megasynth

Viewer • Updated Jul 3, 2023 • 13k • 19

reciprocate/alpaca-eval

Viewer • Updated Jul 3, 2023 • 10.5k • 31 • 1

reciprocate/synth_clean

Viewer • Updated Jul 3, 2023 • 2.37k • 27

reciprocate/vicuna-fair-eval_format-oa

Viewer • Updated Jun 17, 2023 • 66 • 18