-
koreankiwi99/MNLP_M3_dpo_model
0.6B • Updated • 2 -
koreankiwi99/0_predpo_lower_beta_balanced_lower_beta_mnlp_aggregate
0.6B • Updated • 2 -
koreankiwi99/1_predpo_tuned_balanced_lower_beta_mnlp_aggregate
0.6B • Updated • 2 -
koreankiwi99/3_predpo_base_curriculum_lower_beta_mnlp_aggregate
0.6B • Updated • 2
KyuheeKim
koreankiwi99
AI & ML interests
None yet
Organizations
2025_MNLP_M3_DPO
-
koreankiwi99/MNLP_M3_dpo_model
0.6B • Updated • 2 -
koreankiwi99/0_predpo_lower_beta_balanced_lower_beta_mnlp_aggregate
0.6B • Updated • 2 -
koreankiwi99/1_predpo_tuned_balanced_lower_beta_mnlp_aggregate
0.6B • Updated • 2 -
koreankiwi99/3_predpo_base_curriculum_lower_beta_mnlp_aggregate
0.6B • Updated • 2
epfl-lighteval-dpo-datasets
models 86
koreankiwi99/llama-3.1-8b-paraphrase-qlora-10000
Updated
koreankiwi99/0_predpo_lower_beta_balanced_lower_beta_mnlp_aggregate
0.6B • Updated
• 2
koreankiwi99/1_predpo_tuned_balanced_lower_beta_mnlp_aggregate
0.6B • Updated
• 2
koreankiwi99/2_predpo_base_balanced_plus_lower_beta_mnlp_aggregate
0.6B • Updated
• 2
koreankiwi99/3_predpo_base_curriculum_lower_beta_mnlp_aggregate
0.6B • Updated
• 2
koreankiwi99/4_dpo_curriculum_lower_beta_mnlp_aggregate
0.6B • Updated
• 2
koreankiwi99/5_dpo_balanced_plus_lower_beta_mnlp_aggregate
0.6B • Updated
• 2
koreankiwi99/dpo_model_predpo_config_mnlp_aggregate
0.6B • Updated
• 3
koreankiwi99/sft_model_sft_base_mnlp_stem_curriculum
0.6B • Updated
• 2
koreankiwi99/sft_model_sft_base_mnlp_stem_balanced_plus
0.6B • Updated
• 2
datasets 18
koreankiwi99/Nunchi-Bench
Preview
• Updated
• 66 • 1
koreankiwi99/MNLP_M3_dpo_dataset
Viewer
• Updated
• 135k • 3
koreankiwi99/helpsteer3-dpo-general
Viewer
• Updated
• 915 • 8
koreankiwi99/helpsteer3-dpo-stem
Viewer
• Updated
• 243 • 18
koreankiwi99/helpsteer3-dpo-code
Viewer
• Updated
• 432 • 3
koreankiwi99/mtbench-dpo-turn1-gpt4_pair
Viewer
• Updated
• 882 • 3
koreankiwi99/mtbench-dpo-turn1-human
Viewer
• Updated
• 1.28k • 5
koreankiwi99/hh-dpo-eval
Viewer
• Updated
• 8.53k • 3
koreankiwi99/mnlp_stem_curriculum
Viewer
• Updated
• 31.8k • 15
koreankiwi99/mnlp_stem_balanced_plus
Viewer
• Updated
• 40.8k • 7