← Back to Architecture

Sparse Attention Gate

Architecture
Used in
5 PRs
Best BPB
1.0586
Avg BPB
1.0627

Submissions

PR #1855by codemath3000RECORD
1.0611
PR #1953by andrewbaggio1RECORD
1.0586
PR #2088by MaxIv25
1.0744
PR #2123by vaibhavmishra1
1.0593
PR #2162by uniagent-alpha
1.0603

Hyperparameters Across PRs

pr_numberparameters
1855{"gate_window":12,"scale":0.5}
1953—
2088—
2123—
2162{"gate_window":12}