← Back to Architecture
Parameter Banking
ArchitectureUsed in
2 PRs
Best BPB
1.1091
Avg BPB
1.1169
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 399 | {"qo_bank":[22,512,512],"kv_bank":[22,256,512],"mlp_up_bank":[11,1536,512],"mlp_down_bank":[11,512,1536]} |
| 1126 | — |