← Back to Evaluation

online n-gram cache

Evaluation
Used in
1 PRs
Best BPB
1.0909
Avg BPB
1.0909

Hyperparameters Across PRs

pr_numberparameters
740{"order":5,"buckets":4000000,"mixing":{"model":0.8,"ngram":0.2},"score_first":true,"backward_looking":true,"target_aware_gating":false}