reward modeling

classroom

AI & ML interests

None defined yet.

Recent Activity

yifeihe3 authored a paper 17 days ago

Semi-Supervised Reward Modeling via Iterative Self-Training

yifeihe3 authored a paper 17 days ago

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks

yifeihe3 authored a paper 17 days ago

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

View all activity

cornfieldrm 's datasets 118

cornfieldrm/pair-preference-dataset-700K_subset-2-of-3_soup_conf-0.6

Viewer • Updated May 28, 2024 • 192k • 5

cornfieldrm/pair-preference-dataset-700K_subset-2-of-3_soup_conf-0.8

Viewer • Updated May 28, 2024 • 132k • 7

cornfieldrm/pair-preference-dataset-700K_subset-2-of-3_soup_conf-0.9

Viewer • Updated May 28, 2024 • 97.9k • 7

cornfieldrm/pair-preference-dataset-700K_subset-2-of-3_soup-pred

Viewer • Updated May 28, 2024 • 58 • 4

cornfieldrm/pair-preference-dataset-700K_subset-3-of-3_standard

Viewer • Updated May 28, 2024 • 233k • 6

cornfieldrm/pair-preference-dataset-700K_subset-2-of-3_standard

Viewer • Updated May 28, 2024 • 233k • 6

cornfieldrm/pair-preference-dataset-700K_subset-1-of-3_standard

Viewer • Updated May 28, 2024 • 233k • 6

cornfieldrm/pair-preference-dataset-700K_subset-3-of-3

Viewer • Updated May 26, 2024 • 233k • 5

cornfieldrm/pair-preference-dataset-700K_subset-2-of-3

Viewer • Updated May 26, 2024 • 233k • 5

cornfieldrm/pair-preference-dataset-700K_subset-1-of-3

Viewer • Updated May 26, 2024 • 233k • 5

cornfieldrm/ArmoRM-MoE-preference-dataset-v0.1

Viewer • Updated May 6, 2024 • 242k • 5

cornfieldrm/prompt-collection-v0.2

Viewer • Updated May 6, 2024 • 453k • 14

cornfieldrm/prm800k-phase2

Viewer • Updated Apr 28, 2024 • 81.6k • 5

cornfieldrm/prompt-collection-v0.1

Viewer • Updated Apr 26, 2024 • 181k • 6

cornfieldrm/sft-ultrachat_1468K

Viewer • Updated Apr 26, 2024 • 1.47M • 7 • 1

cornfieldrm/datamix-v6.0

Viewer • Updated Apr 24, 2024 • 366k • 7

cornfieldrm/datamix-v5.0

Viewer • Updated Apr 23, 2024 • 339k • 7

cornfieldrm/arena-hard_judgments_gpt4-turbo_position-averaged_debugged

Viewer • Updated Apr 23, 2024 • 17.5k • 6

cornfieldrm/datamix-v4.4

Viewer • Updated Apr 22, 2024 • 569k • 7

cornfieldrm/argilla-capybara-v2

Viewer • Updated Apr 22, 2024 • 29.6k • 5 • 1

cornfieldrm/preference_dataset-standard_format-v2.2

Viewer • Updated Apr 21, 2024 • 769k • 6

cornfieldrm/ultrainteract_preference_standard_format

Viewer • Updated Apr 20, 2024 • 162k • 8

cornfieldrm/argilla-capybara

Viewer • Updated Apr 18, 2024 • 15.1k • 5

cornfieldrm/argilla-intel-orca

Viewer • Updated Apr 18, 2024 • 23.1k • 5

cornfieldrm/argilla-math-preference

Viewer • Updated Apr 18, 2024 • 4.84k • 6

cornfieldrm/ultrasafety

Viewer • Updated Apr 18, 2024 • 12k • 7

cornfieldrm/beavertails-is_safe-denoised

Viewer • Updated Apr 18, 2024 • 75.1k • 6

cornfieldrm/preference_dataset-sft_format-v0.1

Viewer • Updated Apr 15, 2024 • 554k • 5