| language-modelling-on-enwiki8 | Transformer (64 layers) | #24 | Bit per Character (BPC): 1.06Number of params: 235M |
| language-modelling-on-enwiki8 | 64-layer Character Transformer Model | #28 | Bit per Character (BPC): 1.11Number of params: 44M |
| language-modelling-on-hutter-prize | 64-layer Character Transformer Model | #8 | Bit per Character (BPC): 1.06Number of params: 235M |
| language-modelling-on-hutter-prize | 12-layer Character Transformer Model | #11 | Bit per Character (BPC): 1.11Number of params: 44M |
| language-modelling-on-text8 | 64-layer Character Transformer Model | #10 | Bit per Character (BPC): 1.13Number of params: 235M |
| language-modelling-on-text8 | 12-layer Character Transformer Model | #12 | Bit per Character (BPC): 1.18Number of params: 44M |