ojaffe/2026-04-16-048-8b-teacher-kd
0.5B • Updated • 11
OJ PRO
ojaffe
·
AI & ML interests
None yet
Recent Activity
updated a model 3 days ago
ojaffe/2026-04-16-048-8b-teacher-kd published a model 3 days ago
ojaffe/2026-04-16-048-8b-teacher-kd updated a model 3 days ago
ojaffe/2026-04-16-044-488m-lr15e3Organizations
ojaffe/2026-04-16-044-488m-lr15e3
0.5B • Updated • 13
ojaffe/2026-04-16-043-lr3e3-pure-kd
0.4B • Updated • 12
ojaffe/2026-04-15-042-t1-alpha05
0.3B • Updated • 13
ojaffe/2026-04-15-041-pure-kd-t2
0.3B • Updated • 9
ojaffe/2026-04-15-040-large-600m-pure-kd
0.5B • Updated • 13
ojaffe/2026-04-15-039-362m-alpha09
0.4B • Updated • 11
ojaffe/2026-04-15-038-larger-student-pure-kd
0.4B • Updated • 15
ojaffe/2026-04-15-042-llama-style-student
0.2B • Updated • 12
ojaffe/2026-04-15-037-t05-pure-kd
0.3B • Updated • 12
ojaffe/2026-04-15-036-pure-kd
0.3B • Updated • 11
ojaffe/2026-04-15-040-phi2-teacher-pure-kl
0.2B • Updated • 13
ojaffe/2026-04-15-035-t1-alpha09
0.3B • Updated • 11
ojaffe/2026-04-15-039-test-budget
0.2B • Updated • 13
ojaffe/2026-04-15-034-temp-alpha-sweep
0.3B • Updated • 13
ojaffe/2026-04-15-038-pure-kl-small-batch
0.1B • Updated • 12
ojaffe/2026-04-15-033-low-weight-decay
0.3B • Updated • 12
ojaffe/2026-04-15-037-pure-kl-very-high-lr
0.2B • Updated • 12
ojaffe/2026-04-15-032-bigger-student-3b-swa
0.3B • Updated • 12
ojaffe/2026-04-15-036-pure-kl-larger-high-lr
0.2B • Updated • 12
ojaffe/2026-04-15-031-3b-teacher-high-lr-swa
0.2B • Updated • 11
ojaffe/2026-04-15-035-pure-kl-higher-lr
0.2B • Updated • 12
ojaffe/2026-04-15-030-lr3e3-swa
0.2B • Updated • 13
ojaffe/2026-04-15-034-pure-kl-no-topk
0.2B • Updated • 12
ojaffe/20260413-091816-babylm-5f3c-2026-04-15-033-pure-kl-topk500
0.2B • Updated • 13
ojaffe/2026-04-15-029-lr4e3-swa
0.2B • Updated • 12
ojaffe/20260413-091816-babylm-5f3c-2026-04-15-032-pure-kl-topk200
0.2B • Updated • 14
ojaffe/2026-04-15-028-very-high-lr-swa
0.2B • Updated • 14
ojaffe/20260413-091816-babylm-5f3c-2026-04-15-031-pure-kl-t1-large
0.2B • Updated • 16
ojaffe/2026-04-15-027-high-lr-swa
0.2B • Updated • 14