← Back to Architecture
Value Residual Learning
ArchitectureUsed in
3 PRs
Best BPB
0.3212
Avg BPB
0.7904
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 733 | — |
| 745 | — |
| 850 | {"layers":[1,10]} |
| pr_number | parameters |
|---|---|
| 733 | — |
| 745 | — |
| 850 | {"layers":[1,10]} |