37 training sources, one strict schema: 15 general (13 repos), 15 domain, 7 RLHN (MS MARCO, NQ, HotpotQA, FEVER, SciDocs-RR, FiQA, ArguAna).
Hyukkyu Kang
Hyukkyu
AI & ML interests
Natural Language Processing, Information Retrieval, Question Answering
Recent Activity
updated a collection about 4 hours ago
Training — unified schema updated a dataset about 4 hours ago
Hyukkyu/train-rlhn-fever published a dataset about 4 hours ago
Hyukkyu/train-rlhn-feverOrganizations
None yet
models 44
Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-Unlearn-GA-GD-LoRA-v1
Text Generation • 8B • Updated • 301
Hyukkyu/Llama-3.1-8B-RAQUEL-MUSE-Unlearn-GA-GD-LoRA-v1
Text Generation • 8B • Updated • 297
Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-Unlearn-IDK-GD-LoRA-v1
Text Generation • 8B • Updated • 298
Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-Unlearn-RMU-LoRA-v1
Text Generation • 8B • Updated • 279
Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-Unlearn-SAUL-LoRA-v1
Text Generation • 8B • Updated • 286
Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-Unlearn-NPO-GD-LoRA-v1
Text Generation • 8B • Updated • 301
Hyukkyu/Qwen3-8B-Base-RAQUEL-TOFU-Unlearn-GA-GD-LoRA-v1
Text Generation • 8B • Updated • 300
Hyukkyu/Llama-3.1-8B-RAQUEL-MUSE-M-ret-LoRA-v1
Text Generation • 8B • Updated • 453
Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-M-orig-LoRA-v1
Text Generation • 8B • Updated • 764
Hyukkyu/Qwen3-8B-Base-RAQUEL-WMDP-Unlearn-SAUL-LoRA-v1
Text Generation • 8B • Updated • 297
datasets 90
Hyukkyu/train-rlhn-fever
Viewer • Updated • 726k
Hyukkyu/train-rlhn-hotpotqa
Viewer • Updated • 2.42M
Hyukkyu/train-rlhn-nq
Viewer • Updated • 8.3M
Hyukkyu/train-rlhn-msmarco
Viewer • Updated • 17.7M
Hyukkyu/train-rlhn-arguana
Viewer • Updated • 562k • 32
Hyukkyu/train-rlhn-fiqa
Viewer • Updated • 1.19M • 35
Hyukkyu/train-rlhn-scidocsrr
Viewer • Updated • 3.13M • 35
Hyukkyu/train-gerlayqa
Viewer • Updated • 2.44M • 107
Hyukkyu/train-law-stackexchange
Viewer • Updated • 2.48M • 122
Hyukkyu/train-casehold
Viewer • Updated • 4.24M • 106