wdlctc/marin-8b-cpt-plain-lr4e4
8B • Updated • 3
chengluo PRO
wdlctc
AI & ML interests
None yet
Recent Activity
upvoted a paper 19 days ago
SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation upvoted a paper 26 days ago
Self-Supervised Visual On-Policy Distillation upvoted a paper about 1 month ago
Multi-Head Attention ResidualsOrganizations
None yet
wdlctc/marin-8b-cpt-mhar-delta
8B • Updated • 21
wdlctc/open-attnres-0.6b-full
Updated
wdlctc/open-attnres-0.6b-block
0.5B • Updated • 40
wdlctc/open-attnres-0.6b-baseline
0.5B • Updated • 26
wdlctc/open-attnres-full
0.1B • Updated • 3
wdlctc/open-attnres-block
0.1B • Updated • 14
wdlctc/open-attnres-baseline
0.1B • Updated • 16