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/llama3.1_8b_sft-llopa-k28-no_system published a model 1 day ago
jeongseokoh/llama3.1_8b_sft-llopa-k28-no_system updated a model 3 days ago
jeongseokoh/llama3.1_8b_sft-llopa-k24Organizations
models 243
jeongseokoh/llama3.1_8b_sft-llopa-k28-no_system
Updated • 21
jeongseokoh/llama3.1_8b_sft-llopa-k24
Updated • 20
jeongseokoh/llama3.1_8b_sft-llopa-k28
Updated • 23
jeongseokoh/llama3.1_8b_sft-vanilla
Updated • 48
jeongseokoh/tulu3_8b_sft-llopa-k28
Updated • 74
jeongseokoh/tulu3_8b_sft-llopa-k28_fp32
Updated
jeongseokoh/tulu3_8b_sft_vanilla-20-lower-layers
Updated • 18
jeongseokoh/tulu3_8b_sft_vanilla-24-lower-layers
Updated • 114
jeongseokoh/tulu3_8b_sft_vanilla-28-lower-layers
Updated • 98
jeongseokoh/tulu3_8b_sft_vanilla-24-lower-layers_b4
Updated • 49
datasets 37
jeongseokoh/math_gsm8k_mmlu_sameAnswers
Viewer • Updated • 6.46k • 7
jeongseokoh/math_gsm8k_mmlu
Viewer • Updated • 30k • 6
jeongseokoh/SameAnswerDifferentQuestion
Viewer • Updated • 1.86k • 5
jeongseokoh/concat_DPO_for_Mathematics
Viewer • Updated • 120k • 2
jeongseokoh/Original_DPO_for_Mathematics
Viewer • Updated • 78.1k • 3
jeongseokoh/prefix_DPO_for_Mathematics
Viewer • Updated • 41.6k • 3
jeongseokoh/prefix_DPO_preparation
Viewer • Updated • 41.6k • 4
jeongseokoh/GSM8K_for_test_DPO
Viewer • Updated • 1.32k • 4
jeongseokoh/MATH_for_test_DPO
Viewer • Updated • 5k • 4
jeongseokoh/Concatenated_DPO
Viewer • Updated • 120k • 4