← Back to Architecture
Parallel Muon
ArchitectureUsed in
1 PRs
Best BPB
0.1310
Avg BPB
0.1310
Submissions
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 893 | {"layers":11,"dimensions":512} |
| pr_number | parameters |
|---|---|
| 893 | {"layers":11,"dimensions":512} |