Korean Reward Modeling - a heegyu Collection

heegyu 's Collections

Korean Reward Modeling

Korean Pretraining Dataset

Reward Modeling Datasets

Pre-training Dataset

Image Generation

Domain Specific (Math, Code, etc)

Machine Translation

Korean Reward Modeling

updated May 29

Korean Datasets, Reward Models for RLHF

heegyu/KoSafeGuard-8b-0503

Text Generation • Updated 8 days ago • 212 • 4
heegyu/ko-reward-model-helpful-1.3b-v0.2

Text Classification • Updated Jan 10 • 17
heegyu/ko-reward-model-safety-1.3b-v0.2

Text Classification • Updated Jan 13 • 16 • 5
heegyu/ko-reward-model-helpful-roberta-large-v0.1

Text Classification • Updated Dec 31, 2023 • 19 • 1
heegyu/ko-reward-model-safety-roberta-large-v0.1

Text Classification • Updated Dec 31, 2023 • 4
heegyu/ko-reward-model-1.3b-v0.1

Text Classification • Updated Dec 7, 2023 • 9 • 1
heegyu/ko-reward-model-1.3b-v0

Text Classification • Updated Dec 1, 2023 • 42 • 1
heegyu/ko-ultrafeedback-binarized-1.3b

Text Classification • Updated Nov 27, 2023 • 8 • 2
maywell/ko_Ultrafeedback_binarized

Viewer • Updated Nov 9, 2023 • 62k • 63 • 28
maywell/ko_hh-rlhf-20k_filtered

Viewer • Updated Nov 4, 2023 • 19.4k • 49 • 4
heegyu/hh-rlhf-ko

Viewer • Updated Dec 24, 2023 • 169k • 78 • 3
heegyu/PKU-SafeRLHF-ko

Viewer • Updated Dec 31, 2023 • 320k • 52 • 4
heegyu/webgpt_comparisons_ko

Viewer • Updated Dec 5, 2023 • 19.6k • 12 • 2
SJ-Donald/orca-dpo-pairs-ko

Viewer • Updated Jan 24 • 36k • 86 • 7