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
published a dataset about 3 hours ago
Seungjun/clean-math-sft-pool-30k updated a dataset about 3 hours ago
Seungjun/clean-math-sft-pool-30k published a dataset about 4 hours ago
Seungjun/clean-math-sft-poolOrganizations
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 • 15
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 • 10
datasets 32
Seungjun/clean-math-sft-pool-30k
Viewer • Updated • 28.9k
Seungjun/clean-math-sft-pool
Viewer • Updated • 381k
Seungjun/dp_removed_OpenR1-Math-220k
Viewer • Updated • 15.2k • 23
Seungjun/dp_removed_s1K-1.1
Viewer • Updated • 996 • 93
Seungjun/dp_removed_MATH-500
Viewer • Updated • 500 • 66
Seungjun/dp_removed_amc23
Viewer • Updated • 40 • 66
Seungjun/dp_removed_aime_2026
Viewer • Updated • 30 • 54
Seungjun/dp_removed_aime25
Viewer • Updated • 30 • 56
Seungjun/dp_removed_aime_2024
Viewer • Updated • 30 • 54
Seungjun/dp_removed_DAPO-Math-17k-Processed
Viewer • Updated • 14.1k • 116