Focus Your Attention (with Adaptive IIR Filters)
Open paper
Benchmark
Model
Rank
Results
language-modelling-on-enwiki8
Focus
–
Bit per Character (BPC): 0.940
Number of params: 22M
language-modelling-on-text8
Focus
–
Bit per Character (BPC): 0.98
Number of params: 22M
Rank counts only results with a code link.