← Back to Architecture

manifold-guided token interaction graph

Architecture
Used in
1 PRs
Best BPB
0.4380
Avg BPB
0.4380

Submissions

PR #663by raahilg
0.4380

Hyperparameters Across PRs

pr_numberparameters
663{"vocab":1024,"spectral_dims":320,"hops":4,"attention_heads":2,"hidden_dim":500}