MultiHashFormer: Hash-based Generative Language Models
Open paper
Benchmark
Model
Rank
Results
question-answering-on-copa-zero-shot
MHF (H3B10K)
#4
Accuracy: 71.0
language-modelling-on-lambada
MHF (H4B4K)
#61
Accuracy: 30.27
Rank counts only results with a code link.