← Back to Architecture
MLP4
ArchitectureUsed in
2 PRs
Best BPB
1.3092
Avg BPB
1.3938
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 408 | {"mlp_mult":4} |
| 759 | — |
| pr_number | parameters |
|---|---|
| 408 | {"mlp_mult":4} |
| 759 | — |