LLaMA 65B + CFG (0-shot)

Reported on 2 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Common Sense ReasoningonARC (Easy)
Accuracy· 2023-06-30
84.2
best: 95.2 (ST-MoE-32B 269B (fine-tuned))
Stay on topic with Classifier-Free Guidance arXiv:2306.17806
Sentence CompletiononHellaSwag
Accuracy· 2023-06-30
86.3
best: 96.1 (CompassMTL 567M with Tailor)
Stay on topic with Classifier-Free Guidance arXiv:2306.17806