Memorization On Big Bench Hindu Knowledge
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
模型名称 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| PaLM-540B (few-shot, k=5) | 95.4 | PaLM: Scaling Language Modeling with Pathways | |
| PaLM-62B (few-shot, k=5) | 77.7 | PaLM: Scaling Language Modeling with Pathways | |
| Gopher-280B (few-shot, k=5) | 80 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher |
0 of 3 row(s) selected.