Hyena Hierarchy: Towards Larger Convolutional Language Models
Open paper
Benchmark
Model
Rank
Results
language-modelling-on-wikitext-103
Hyena-3-slim
#42
Test perplexity: 18.5
language-modelling-on-wikitext-103
Hyena-3
#43
Test perplexity: 18.6
question-answering-on-boolq
Hyena
#115
Accuracy: 51.8
Rank counts only results with a code link.