Downloads · 30 days
0
rookierufus/JEPA_CMPR_ATTENTION
JEPA_CMPR_ATTENTION is a machine learning model from rookierufus. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Attention-memory JEPA chunk-mask training on Soft-TOME tarcontinuationimportance (all shards).
Downloads · 30 days
0
Access
Public
Updated Jul 30, 2026
Repo size
1.6 GB
Likes
0
Public
Click a slice to open those files.
.pt1.6 GB · 100%
From the Hugging Face model README
Attention-memory JEPA chunk-mask training on Soft-TOME tar_continuation_importance (all shards).
checkpoints/attn-chunkmask-...-allshards/ — early run (step_000000.pt, step_000263.pt)checkpoints/attn-chunkmask-...-allshards-resume264/ — resume to full schedule (step_000526.pt, step_000789.pt, step_001051.pt final)logs/ — training logs for both runsFinal checkpoint: checkpoints/attn-chunkmask-Beff256-B64-accum4-K4-lam005-ret0.2-predSA2-t1-ep4-allshards-resume264/step_001051.pt