Seungjun/llama3.2-1b-helpfulness-reward-model
1B • Updated • 1
🔄 In a Training Loop
Seungjun Lee
Seungjun
·
AI & ML interests
LLM Post-Training
Recent Activity
liked a dataset 18 days ago
Seungjun/Korean-Olympiad-TDCS-3K updated a dataset 18 days ago
Seungjun/Korean-Olympiad-TDCS-3K published a dataset 18 days ago
Seungjun/Korean-Olympiad-TDCS-3KOrganizations
models 66
Seungjun/llama3.2-1b-safety-reward-model
1B • Updated • 1
Seungjun/gemma-3n-E2B-it-4bit
2B • Updated • 7
Seungjun/MidnightHammer_91
Updated
Seungjun/MidnightHammer_61
Updated
Seungjun/llama-3.2-1B-finetuned-unsafe-pt-step45
Text Generation • 1B • Updated • 7
Seungjun/real_new_llama_rl_model_step61
Updated
Seungjun/real_new_llama_rl_model_step76
Updated
Seungjun/real_new_llama_rl_model_step46
Updated
Seungjun/llama-3.2-1B-finetuned-unsafe-pt
Text Generation • 1B • Updated • 5
datasets 22
Seungjun/Korean-Olympiad-TDCS-3K
Viewer • Updated • 3.3k • 89 • 1
Seungjun/Korean-DeepMath-with-Difficulty
Viewer • Updated • 102k • 47
Seungjun/openorca-50k
Viewer • Updated • 23k • 4 • 1
Seungjun/hint_alpaca_ceaser
Viewer • Updated • 52k • 2 • 1
Seungjun/alpaca_ceaser
Viewer • Updated • 52k • 4 • 1
Seungjun/safet_98_prompts
Viewer • Updated • 92 • 2 • 1
Seungjun/safet_200_prompts
Viewer • Updated • 200 • 3 • 1
Seungjun/toxic_llama_v2_c4_ptx
Viewer • Updated • 10k • 6 • 1
Seungjun/toxic_llama_v2_cleaned_alpaca
Viewer • Updated • 31.3k • 12 • 1
Seungjun/openorca-caesar-50k
Viewer • Updated • 23k • 5 • 1