← Back to Architecture
1+7+1 layer stack
ArchitectureUsed in
1 PRs
Best BPB
1.1194
Avg BPB
1.1194
Submissions
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 625 | {"reasoning_layer":1,"completion_blocks":7,"validation_layer":1,"BigramHash_vocab_size":1536,"RoPE_dims":16} |