Checkpoints of the paper Depth Memory: the final checkpoint of every learning-rate sweep run of PreLN, AttnRes, mHC and LDM at 400M and 1.5B.
David González Martínez
davidgonmar
AI & ML interests
None yet
Recent Activity
updated a model 6 days ago
davidgonmar/depth-memory-1.5b-ldm updated a model 6 days ago
davidgonmar/depth-memory-1.5b-mhc updated a model 6 days ago
davidgonmar/depth-memory-1.5b-attnres-blockOrganizations
None yet
models 10
davidgonmar/depth-memory-1.5b-ldm
Updated
davidgonmar/depth-memory-1.5b-mhc
Updated
davidgonmar/depth-memory-1.5b-attnres-block
Updated • 1
davidgonmar/depth-memory-1.5b-preln
Updated
davidgonmar/depth-memory-400m-preln
Updated
davidgonmar/depth-memory-400m-ldm-dk4
Updated
davidgonmar/depth-memory-400m-ldm
Updated
davidgonmar/depth-memory-400m-mhc
Updated
davidgonmar/depth-memory-400m-attnres-block
Updated
davidgonmar/depth-memory-400m-attnres-full
Updated
datasets 0
None public yet