← Back to Architecture

SLOT

Architecture
Used in
2 PRs
Best BPB
0.7406
Avg BPB
1.0942

Submissions

PR #1321by anthony-maio
0.7406
PR #1425by dentity007
1.4479

Hyperparameters Across PRs

pr_numberparameters
1321{"hidden_delta_shape":"[bsz, 1, 512]","logit_bias_shape":"[bsz, 1, 1024]"}
1425—