| Benchmark | Model | Rank | Results |
|---|---|---|---|
| language-modelling-on-one-billion-word | H-Transformer-1D Nr=16 (Base) | #24 | Number of params: 53MValidation perplexity: 23.95 |
| language-modelling-on-one-billion-word | H-Transformer-1D Nr=16 (Large) | #25 | Number of params: 144MValidation perplexity: 20.25 |