reward modeling

classroom

AI & ML interests

None defined yet.

Recent Activity

tengyangx authored a paper 9 days ago

Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences

tengyangx authored a paper 9 days ago

Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF

tengyangx authored a paper 9 days ago

Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts

View all activity

cornfieldrm 's datasets 118

cornfieldrm/pair-preference-dataset-700K_subset-15-out-of-16_llama3-8b-it_1-of-16_slic

Viewer • Updated Jun 7, 2024 • 51.4k • 4

cornfieldrm/pair-preference-dataset-700K_subset-15-out-of-16_llama3-8b-it_1-of-16_

Viewer • Updated Jun 7, 2024 • 51.4k • 4

cornfieldrm/pair-preference-dataset-700K_subset-9-out-of-10_slic

Viewer • Updated Jun 6, 2024 • 629k • 3

cornfieldrm/pair-preference-dataset-700K_subset-1-out-of-10_slic

Viewer • Updated Jun 6, 2024 • 69.9k • 4

cornfieldrm/pair-preference-dataset-700K_subset-9-out-of-10_standard

Viewer • Updated Jun 6, 2024 • 629k • 4

cornfieldrm/pair-preference-dataset-700K_subset-1-out-of-10_standard

Viewer • Updated Jun 6, 2024 • 69.9k • 4

cornfieldrm/pair-preference-dataset-700K_subset-4-of-4_llama3-8b-it_iter2_conf-0.8_slic

Viewer • Updated Jun 6, 2024 • 94.5k • 4

cornfieldrm/pair-preference-dataset-700K_subset-4-of-4_llama3-8b-it_iter2_conf-0.8

Viewer • Updated Jun 6, 2024 • 94.5k • 4

cornfieldrm/pair-preference-dataset-700K_subset-3-of-4_llama3-8b-it_iter2_conf-0.8_slic

Viewer • Updated Jun 6, 2024 • 94.5k • 4

cornfieldrm/pair-preference-dataset-700K_subset-3-of-4_llama3-8b-it_iter2_conf-0.8

Viewer • Updated Jun 6, 2024 • 94.5k • 4

cornfieldrm/pair-preference-dataset-700K_subset-2-of-4_llama3-8b-it_iter2_conf-0.8_slic

Viewer • Updated Jun 6, 2024 • 94.5k • 4

cornfieldrm/pair-preference-dataset-700K_subset-2-of-4_llama3-8b-it_iter2_conf-0.8

Viewer • Updated Jun 6, 2024 • 94.5k • 4

cornfieldrm/pair-preference-dataset-700K_subset-4-of-4_llama3-8b-it_0.25_sft_conf-0.8_slic

Viewer • Updated Jun 5, 2024 • 70.7k • 4

cornfieldrm/pair-preference-dataset-700K_subset-3-of-4_llama3-8b-it_0.25_sft_conf-0.8_slic

Viewer • Updated Jun 5, 2024 • 70.6k • 4

cornfieldrm/pair-preference-dataset-700K_subset-4-of-4_llama3-8b-it_0.25_sft_conf-0.8

Viewer • Updated Jun 5, 2024 • 70.7k • 3

cornfieldrm/pair-preference-dataset-700K_subset-2-of-4_llama3-8b-it_0.25_sft_conf-0.8_slic

Viewer • Updated Jun 5, 2024 • 70.7k • 4

cornfieldrm/pair-preference-dataset-700K_subset-3-of-4_llama3-8b-it_0.25_sft_conf-0.8

Viewer • Updated Jun 5, 2024 • 70.6k • 4

cornfieldrm/pair-preference-dataset-700K_subset-2-of-4_llama3-8b-it_0.25_sft_conf-0.8

Viewer • Updated Jun 5, 2024 • 70.7k • 4

cornfieldrm/pair-preference-dataset-700K_slic

Viewer • Updated Jun 2, 2024 • 699k • 4

cornfieldrm/pair-preference-dataset-700K_subset-4-of-4_gemma-2b_1of4_iter3_conf-0.8_slic

Viewer • Updated Jun 2, 2024 • 75.9k • 4

cornfieldrm/pair-preference-dataset-700K_subset-3-of-4_gemma-2b_1of4_iter3_conf-0.8_slic

Viewer • Updated Jun 2, 2024 • 75.8k • 3

cornfieldrm/pair-preference-dataset-700K_subset-2-of-4_gemma-2b_1of4_iter3_conf-0.8_slic

Viewer • Updated Jun 2, 2024 • 76.3k • 3

cornfieldrm/pair-preference-dataset-700K_subset-4-of-4_gemma-2b_1of4_iter3_conf-0.8_bs128_lr1e-5_conf-0.8

Viewer • Updated Jun 2, 2024 • 75.9k • 4

cornfieldrm/pair-preference-dataset-700K_subset-3-of-4_gemma-2b_1of4_iter3_conf-0.8_bs128_lr1e-5_conf-0.8

Viewer • Updated Jun 2, 2024 • 75.8k • 4

cornfieldrm/pair-preference-dataset-700K_subset-2-of-4_gemma-2b_1of4_iter3_conf-0.8_bs128_lr1e-5_conf-0.8

Viewer • Updated Jun 2, 2024 • 76.3k • 4

cornfieldrm/pair-preference-dataset-700K_subset-4-of-4_gemma-2b_1of4_iter3_conf-0.9_slic

Viewer • Updated May 31, 2024 • 44.8k • 4

cornfieldrm/pair-preference-dataset-700K_subset-3-of-4_gemma-2b_1of4_iter3_conf-0.9_slic

Viewer • Updated May 31, 2024 • 44.9k • 3

cornfieldrm/pair-preference-dataset-700K_subset-2-of-4_gemma-2b_1of4_iter3_conf-0.9_slic

Viewer • Updated May 31, 2024 • 45.2k • 4

cornfieldrm/pair-preference-dataset-700K_subset-4-of-4_gemma-2b_1of4_iter1_conf-0.8_slic

Viewer • Updated May 31, 2024 • 76.9k • 4

cornfieldrm/pair-preference-dataset-700K_subset-3-of-4_gemma-2b_1of4_iter1_conf-0.8_slic

Viewer • Updated May 31, 2024 • 77k • 4