Language Modeling on 1BW zero-shot
43.91PerplexityARMD
Evaluation results
| Method | Links | |
|---|---|---|
| ARMDModel Size=Medium, Training Steps=300K, Evaluation Protocol=Zero-shot2026.01 | 43.91 | |
| ARMDModel Size=Medium, Training Steps=120K, Evaluation Protocol=Zero-shot2026.01 | 45.49 | |
| ARMDModel Size=Small, Training Steps=400K, Evaluation Protocol=Zero-shot2026.01 | 52.94 | |
| ARMDModel Size=Small, Training Steps=180K, Evaluation Protocol=Zero-shot2026.01 | 53.18 | |
| GPT-2Model Size=Medium, Evaluation Protocol=Zero-shot2026.01 | 55.72 | |
| RADDModel Size=Medium, Training Steps=400K, Evaluation Protocol=Zero-shot2026.01 | 60.32 | |
| SEDDModel Size=Medium, Training Steps=400K, Evaluation Protocol=Zero-shot2026.01 | 61.19 | |
| RADDModel Size=Small, Training Steps=400K, Evaluation Protocol=Zero-shot2026.01 | 72.99 | |
| GPT-2Model Size=Small, Evaluation Protocol=Zero-shot2026.01 | 75.2 | |
| SEDDModel Size=Small, Training Steps=400K, Evaluation Protocol=Zero-shot2026.01 | 79.29 | |
| PLAIDModel Size=Small, Training Steps=600K, Evaluation Protocol=Zero-shot2026.01 | 91.12 | |
| SEDD-UniformModel Size=Small, Training Steps=400K, Evaluation Protocol=Zero-shot2026.01 | 101.37 | |
| D3PMModel Size=Small, Evaluation Protocol=Zero-shot2026.01 | 138.92 |