Text Generation on OpenWebText
Metric: eval_loss (lower is better)
Metric: eval_loss (lower is better)
| # | Model↕ | eval_loss▲ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GPT2-Hermite | 2.91 | No | Polynomial, trigonometric, and tropical activati... | 2025-02-03 | Code |
| 2 | GPT2-81M-LOOP | 3.11 | No | Loop Neural Networks for Parameter Sharing | 2024-09-21 | - |
| 3 | GPT2-124M | 3.12 | No | - | - | Code |