-
jeongseokoh/llama3.1_8b_sft-llopa-k28-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 15 -
jeongseokoh/llama3.1_8b_sft-llopa-k24-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 16 -
jeongseokoh/llama3.1_8b_sft-llopa-k20-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 21 -
jeongseokoh/llama3.1_8b_sft-llopa-k16-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 18
jeongseokoh
jeongseokoh
·
AI & ML interests
Large Language Models, Efficient LLM, Trustworthy AI
Recent Activity
updated a collection about 18 hours ago
LLoPA updated a model 1 day ago
jeongseokoh/llama3.1_8b_sft-llopa-k24-with_system published a model 1 day ago
jeongseokoh/llama3.1_8b_sft-llopa-k24-with_systemOrganizations
LLoPA Downstream Task Models
-
jeongseokoh/llama3.1_8b_sft-llopa-k28-no_system-teacher_cache_overall.correct_only.all.q60000
Updated • 14 -
jeongseokoh/llama3.1_8b_sft-llopa-k24-no_system-teacher_cache_overall.correct_only.all.q60000
Updated • 15 -
jeongseokoh/llama3.1_8b_sft-llopa-k20-no_system-teacher_cache_overall.correct_only.all.q60000
Updated • 13 -
jeongseokoh/llama3.1_8b_sft-llopa-k16-no_system-teacher_cache_overall.correct_only.all.q60000
Updated • 15
LLoPA Freeze Layers
-
jeongseokoh/llama3.1_8b_sft-llopa-k28-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 15 -
jeongseokoh/llama3.1_8b_sft-llopa-k24-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 16 -
jeongseokoh/llama3.1_8b_sft-llopa-k20-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 21 -
jeongseokoh/llama3.1_8b_sft-llopa-k16-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 18
LLoPA Downstream Task Models
-
jeongseokoh/llama3.1_8b_sft-llopa-k28-no_system-teacher_cache_overall.correct_only.all.q60000
Updated • 14 -
jeongseokoh/llama3.1_8b_sft-llopa-k24-no_system-teacher_cache_overall.correct_only.all.q60000
Updated • 15 -
jeongseokoh/llama3.1_8b_sft-llopa-k20-no_system-teacher_cache_overall.correct_only.all.q60000
Updated • 13 -
jeongseokoh/llama3.1_8b_sft-llopa-k16-no_system-teacher_cache_overall.correct_only.all.q60000
Updated • 15
models 304
jeongseokoh/llama3.1_8b_sft-llopa-k24-with_system
Updated • 20
jeongseokoh/llama3.1_8b_sft-llopa-k28-with_system
Updated • 24
jeongseokoh/llama3.1_8b_sft-llopa-k20
Updated • 17
jeongseokoh/llama3.1_8b_sft-vanilla-teacher_cache_overall.correct_only.all.q60000.r1-freeze-lower-k24
Updated
jeongseokoh/llama3.1_8b_sft-llopa-k16
Updated • 23
jeongseokoh/llama3.1_8b_sft-llopa-k20-with_system
Updated • 31
jeongseokoh/Llama-3.1-8B-Instruct-teacher_cache_overall.correct_only.all.q60000.r1-llopa-k16-no_system
Updated • 16
jeongseokoh/llama3.1_8b_sft-llopa-k16-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 18
jeongseokoh/llama3.1_8b_sft-llopa-k20-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 21
jeongseokoh/llama3.1_8b_sft-llopa-k28-no_system-teacher_cache_overall.correct_only_lower_freeze
Updated • 15
datasets 37
jeongseokoh/math_gsm8k_mmlu_sameAnswers
Viewer • Updated • 6.46k • 4
jeongseokoh/math_gsm8k_mmlu
Viewer • Updated • 30k • 11
jeongseokoh/SameAnswerDifferentQuestion
Viewer • Updated • 1.86k • 13
jeongseokoh/concat_DPO_for_Mathematics
Viewer • Updated • 120k • 4
jeongseokoh/Original_DPO_for_Mathematics
Viewer • Updated • 78.1k • 5
jeongseokoh/prefix_DPO_for_Mathematics
Viewer • Updated • 41.6k • 3
jeongseokoh/prefix_DPO_preparation
Viewer • Updated • 41.6k • 8
jeongseokoh/GSM8K_for_test_DPO
Viewer • Updated • 1.32k • 3
jeongseokoh/MATH_for_test_DPO
Viewer • Updated • 5k • 4
jeongseokoh/Concatenated_DPO
Viewer • Updated • 120k • 4