ojaffe/20260410-100218-babylm-2026-04-10-012-kd-regularized
0.3B • Updated • 16
OJ PRO
ojaffe
·
AI & ML interests
None yet
Recent Activity
updated a model 20 minutes ago
ojaffe/20260413-091816-babylm-5f3c-2026-04-15-031-pure-kl-t1-large published a model 21 minutes ago
ojaffe/20260413-091816-babylm-5f3c-2026-04-15-031-pure-kl-t1-large updated a model 33 minutes ago
ojaffe/2026-04-15-027-high-lr-swaOrganizations
ojaffe/20260410-100218-babylm-2026-04-10-011-kd-phi2
Updated • 11
ojaffe/20260410-100218-babylm-2026-04-10-010-kd-qwen
0.4B • Updated • 15
ojaffe/2026-04-10-009000-kd-gpt2-tuned-v2
89.2M • Updated • 17
ojaffe/2026-04-10-144000-pergame-models
Updated
ojaffe/20260410-100218-babylm-2026-04-10-009-data-quality
0.3B • Updated • 14
ojaffe/20260410-085323-small-world-model-2026-04-10-161000-depthwise-sep-convlstm-96ch
Updated • 14
ojaffe/20260410-085323-small-world-model-2026-04-10-151000-hybrid-large-128ch
Updated • 13
ojaffe/20260410-100218-babylm-2026-04-10-008-kd-optimized
0.3B • Updated • 15
ojaffe/20260410-085323-small-world-model-2026-04-10-150000-large-model-128ch
Updated • 13
ojaffe/20260410-085323-small-world-model-2026-04-10-145000-hybrid-ssim-l1-loss
Updated • 9
ojaffe/20260410-085323-small-world-model-2026-04-10-141000-attention-channel
Updated • 12
ojaffe/2026-04-10-122500-finetune-multistep
Updated
ojaffe/20260410-085323-small-world-model-2026-04-10-140700-ensemble-three-model
Updated • 12
ojaffe/20260410-085323-small-world-model-2026-04-10-140600-ensemble-diverse-v2
Updated • 13
ojaffe/20260410-085323-small-world-model-2026-04-10-140500-ensemble-diverse-v1
Updated • 12
ojaffe/20260410-085323-small-world-model-2026-04-10-140300-large-motion-loss
Updated • 24 • 1
ojaffe/20260410-085323-small-world-model-2026-04-10-140200-ensemble-approach
Updated • 10
ojaffe/20260410-085323-small-world-model-2026-04-10-140100-regularization-dropout
Updated • 6
ojaffe/20260410-085323-small-world-model-2026-04-10-140000-motion-auxiliary-loss
Updated • 13
ojaffe/20260410-085323-small-world-model-2026-04-10-121500-scheduled-sampling-lr-schedule
Updated • 14
ojaffe/20260410-085323-small-world-model-2026-04-10-110000-scheduled-sampling
Updated • 13
ojaffe/20260410-085323-small-world-model-2026-04-10-104000-convlstm-larger
Updated • 13
ojaffe/20260410-085323-small-world-model-2026-04-10-102000-convlstm-ssim
Updated • 12
ojaffe/20260410-085323-small-world-model-2026-04-10-090000-convlstm-baseline
Updated • 12
ojaffe/2026-04-09-320000-safety-specialist-14b-v1
15B • Updated • 11
ojaffe/2026-04-09-310000-lora-dpo-14b-v1
Text Generation • 15B • Updated • 279
ojaffe/2026-04-10-010000-flow-warp-v7b
Updated • 12
ojaffe/2026-04-09-300000-act-14b-truthfulness-v1
15B • Updated • 13
ojaffe/world-model-0
Updated