LSC for Majority selection in Short- and Long-form generation
jeongseokoh
jeongseokoh
·
AI & ML interests
Large Language Models, Efficient LLM, Trustworthy AI
Recent Activity
updated
a model 1 day ago
jeongseokoh/tulu3_8b_sft_vanilla-24-lower-layers published
a model 1 day ago
jeongseokoh/tulu3_8b_sft_vanilla-24-lower-layers updated
a model 2 days ago
jeongseokoh/tulu3_8b_sft_vanilla-28-lower-layers Organizations
models 234
jeongseokoh/tulu3_8b_sft_vanilla-24-lower-layers
Updated
• 14
jeongseokoh/tulu3_8b_sft_vanilla-28-lower-layers
Updated
• 23
jeongseokoh/tulu3_8b_sft_vanilla
Updated
• 20
jeongseokoh/Llama-3.1-8B-llopa-full-k24-best-from-base
8B • Updated
• 11
jeongseokoh/Llama-3.3-70B-Instruct-gold-pref50-spec0-taskall-teacher_cache_overall-nobos-LLoPA_GC
Updated
• 2
jeongseokoh/Llama-3.3-70B-Instruct-gold-pref60-spec0-taskall-teacher_cache_overall-nobos-LLoPA_GC
Updated
jeongseokoh/Llama-3.3-70B-Instruct-gold-pref80-spec0-taskall-teacher_cache_overall-nobos-LLoPA_GC
Updated
jeongseokoh/LatentSC_llama3.1_8b_6SummaryTokens
Text Generation • 8B • Updated
• 3
jeongseokoh/Llama31-8B-Inst-gold-lopa-pref13-spec0-teacher_cache-fullattn
Updated
jeongseokoh/Llama31-8B-Inst-gold-lopa-pref15-spec0-teacher_cache-fullattn
Updated
datasets 37
jeongseokoh/math_gsm8k_mmlu_sameAnswers
Viewer
• Updated
• 6.46k • 7
jeongseokoh/math_gsm8k_mmlu
Viewer
• Updated
• 30k • 5
jeongseokoh/SameAnswerDifferentQuestion
Viewer
• Updated
• 1.86k • 6
jeongseokoh/concat_DPO_for_Mathematics
Viewer
• Updated
• 120k • 5
jeongseokoh/Original_DPO_for_Mathematics
Viewer
• Updated
• 78.1k • 4
jeongseokoh/prefix_DPO_for_Mathematics
Viewer
• Updated
• 41.6k • 5
jeongseokoh/prefix_DPO_preparation
Viewer
• Updated
• 41.6k • 5
jeongseokoh/GSM8K_for_test_DPO
Viewer
• Updated
• 1.32k • 5
jeongseokoh/MATH_for_test_DPO
Viewer
• Updated
• 5k • 6
jeongseokoh/Concatenated_DPO
Viewer
• Updated
• 120k • 5