jeongseokoh
jeongseokoh
·
AI & ML interests
Large Language Models, Efficient LLM, Trustworthy AI
Recent Activity
published a model 35 minutes ago
jeongseokoh/llama3.1_8b_sft_LoRA-CE-v1_SPEED-24-BoS-InterleavedAnchor128 updated a model about 1 hour ago
jeongseokoh/llama3.1_8b_sft_LoRA-CE-v1_SPEED-28-BoS-InterleavedAnchor128 published a model about 1 hour ago
jeongseokoh/llama3.1_8b_sft_LoRA-CE-v1_SPEED-28-BoS-InterleavedAnchor128Organizations
models 360
jeongseokoh/llama3.1_8b_sft_LoRA-CE-v1_SPEED-24-BoS-InterleavedAnchor128
Updated
jeongseokoh/llama3.1_8b_sft_LoRA-CE-v1_SPEED-28-BoS-InterleavedAnchor128
Updated
jeongseokoh/Gemma2-9B-it_SPEED-37-BoS
Text Generation • Updated • 23
jeongseokoh/Qwen3-8B_SPEED-34-BoS_PrefixBoS
Text Generation • Updated • 18
jeongseokoh/Qwen3-8B_SPEED-30-BoS-Query_PrefixBoS
Text Generation • Updated
jeongseokoh/Qwen3-8B_SPEED-27-BoS-Query_PrefixBoS
Text Generation • Updated
jeongseokoh/Qwen3-8B_SPEED-24-BoS-Query_PrefixBoS
Text Generation • Updated
jeongseokoh/Llama-3.1-8B-Instruct_SPEED-28-BoS-Query
Text Generation • Updated
jeongseokoh/Llama-3.1-8B-Instruct_SPEED-24-BoS-Query
Text Generation • Updated • 1
jeongseokoh/Qwen3-8B-Base_SPEED-30-BoS_PrefixBoS
Text Generation • Updated • 1
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 • 8
jeongseokoh/concat_DPO_for_Mathematics
Viewer • Updated • 120k • 37
jeongseokoh/Original_DPO_for_Mathematics
Viewer • Updated • 78.1k • 11
jeongseokoh/prefix_DPO_for_Mathematics
Viewer • Updated • 41.6k • 77
jeongseokoh/prefix_DPO_preparation
Viewer • Updated • 41.6k • 12
jeongseokoh/GSM8K_for_test_DPO
Viewer • Updated • 1.32k • 6
jeongseokoh/MATH_for_test_DPO
Viewer • Updated • 5k • 5
jeongseokoh/Concatenated_DPO
Viewer • Updated • 120k • 12