← Back to Architecture
GELU pre-enrichment
ArchitectureUsed in
4 PRs
Best BPB
0.3922
Avg BPB
0.9982
Submissions
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 810 | {"input_dim":512,"hidden_dim":768,"output_dim":512} |
| 972 | {"dimensions":[512,768,512]} |
| 978 | {"input_dim":512,"hidden_dim":768} |
| 996 | {"input_dim":512,"hidden_dim":768,"output_dim":512} |