KyuheeKim
koreankiwi99
AI & ML interests
None yet
Organizations
models 86
koreankiwi99/llama-3.1-8b-paraphrase-qlora-10000
Updated
koreankiwi99/0_predpo_lower_beta_balanced_lower_beta_mnlp_aggregate
0.6B • Updated
koreankiwi99/1_predpo_tuned_balanced_lower_beta_mnlp_aggregate
0.6B • Updated
koreankiwi99/2_predpo_base_balanced_plus_lower_beta_mnlp_aggregate
0.6B • Updated
koreankiwi99/3_predpo_base_curriculum_lower_beta_mnlp_aggregate
0.6B • Updated
koreankiwi99/4_dpo_curriculum_lower_beta_mnlp_aggregate
0.6B • Updated
koreankiwi99/5_dpo_balanced_plus_lower_beta_mnlp_aggregate
0.6B • Updated
koreankiwi99/dpo_model_predpo_config_mnlp_aggregate
0.6B • Updated • 1
koreankiwi99/sft_model_sft_base_mnlp_stem_curriculum
0.6B • Updated
koreankiwi99/sft_model_sft_base_mnlp_stem_balanced_plus
0.6B • Updated
datasets 18
koreankiwi99/Nunchi-Bench
Preview • Updated • 27 • 1
koreankiwi99/MNLP_M3_dpo_dataset
Viewer • Updated • 135k • 4
koreankiwi99/helpsteer3-dpo-general
Viewer • Updated • 915 • 3
koreankiwi99/helpsteer3-dpo-stem
Viewer • Updated • 243 • 5
koreankiwi99/helpsteer3-dpo-code
Viewer • Updated • 432 • 3
koreankiwi99/mtbench-dpo-turn1-gpt4_pair
Viewer • Updated • 882 • 7
koreankiwi99/mtbench-dpo-turn1-human
Viewer • Updated • 1.28k • 3
koreankiwi99/hh-dpo-eval
Viewer • Updated • 8.53k • 3
koreankiwi99/mnlp_stem_curriculum
Viewer • Updated • 31.8k • 4
koreankiwi99/mnlp_stem_balanced_plus
Viewer • Updated • 40.8k • 3