leonli66/rl-forgetting-polaris-8gpu-results
Updated • 109
Leon Li PRO
leonli66
P(doom) 10%
AI & ML interests
None yet
Organizations
leonli66/stage3-final-mixture-20260910-packed
Viewer • Updated • 3.56M • 121
leonli66/stage3-final-mixture-20260910-raw
Viewer • Updated • 21.7M • 1.28k
leonli66/stage3-real-expansion-agent-teacher-separated-pilot
Viewer • Updated • 5 • 28
leonli66/stage3-real-expansion-agent
Viewer • Updated • 10 • 23
leonli66/stage3-synthetic-expansion-agent
Viewer • Updated • 3 • 12
leonli66/stage3-synthetic-structured-retrieval
Viewer • Updated • 82 • 14
leonli66/stage3-final-mixture-cot50
Viewer • Updated • 20.3M • 976
leonli66/stage3-16384-ultra-short
Viewer • Updated • 1.88M • 89
leonli66/stage3-16384-short
Viewer • Updated • 1.96M • 31
leonli66/stage3-16384
Viewer • Updated • 2.05M • 21
leonli66/post_train_final
Viewer • Updated • 17.4M • 179
leonli66/reasoning_relabel_235b
Viewer • Updated • 2.36M • 285
leonli66/post_train_235b_data
Viewer • Updated • 4.16M • 65
leonli66/reasoning_relabel
Viewer • Updated • 4.86M • 127
leonli66/stage3-mixture-clean
Viewer • Updated • 15.1M • 277
leonli66/stage3-final-mixture
Viewer • Updated • 20.3M • 108
leonli66/stage3-32768
Viewer • Updated • 1.35M • 23
leonli66/stage3-32768-full
Viewer • Updated • 2.6M • 54
leonli66/post_train_30b_data
Viewer • Updated • 7.29M • 37
leonli66/stage2-16384
Viewer • Updated • 6.16M • 38
leonli66/stage1-16384
Viewer • Updated • 2.62M • 34
leonli66/stage0-16384
Viewer • Updated • 1.31M • 63
leonli66/compression-pretraining-data
Viewer • Updated • 194M • 182