Leon Li PRO
leonli66
AI & ML interests
None yet
Organizations
models 11
leonli66/rl_C6p5e19_680m_alpha2.000_beta0.030
Updated
leonli66/rl_C6p5e18_20m_alpha1.000_beta0.008
Updated
leonli66/rl_C6p5e19_200m_alpha0.400_beta0.007
Updated
leonli66/rl_C6p5e19_50m_alpha0.180_beta0.002
Updated
leonli66/rl_C6p5e19_680m_alpha0.750_beta0.030
Updated
leonli66/rl_C6p5e19_200m_alpha1.000_beta0.007
Updated
leonli66/rl_C6p5e19_200m_alpha0.750_beta0.007
Updated
leonli66/rl_C6p5e18_680m_alpha1.000_beta0.296
Updated
leonli66/rl_C6p5e19_680m_alpha1.500_beta0.030
Updated
leonli66/rl_C6p5e18_680m_alpha0.750_beta0.296
Updated
datasets 24
leonli66/rl-forgetting-polaris-8gpu-results
Updated • 67
leonli66/stage3-final-mixture-20260910-packed
Viewer • Updated • 3.56M • 75
leonli66/stage3-final-mixture-20260910-raw
Viewer • Updated • 21.7M • 1.19k
leonli66/stage3-real-expansion-agent-teacher-separated-pilot
Viewer • Updated • 5 • 61
leonli66/stage3-real-expansion-agent
Viewer • Updated • 10 • 21
leonli66/stage3-synthetic-expansion-agent
Viewer • Updated • 3 • 21
leonli66/stage3-synthetic-structured-retrieval
Viewer • Updated • 82 • 31
leonli66/stage3-final-mixture-cot50
Viewer • Updated • 20.3M • 804
leonli66/stage3-16384-ultra-short
Viewer • Updated • 1.88M • 78
leonli66/stage3-16384-short
Viewer • Updated • 1.96M • 43