Text Generation On Openwebtext
评估指标
eval_loss
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||
|---|---|---|---|
| GPT2-124M | 3.12 | Language Models are Unsupervised Multitask Learners | - |
| GPT2-81M-LOOP | 3.11 | Loop Neural Networks for Parameter Sharing | - |
| GPT2-Hermite | 2.91 | Polynomial, trigonometric, and tropical activations |
0 of 3 row(s) selected.