HyperAIHyperAI

Command Palette

Search for a command to run...

Text Generation On Sciq

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Paper TitleRepository
LLaMA-65B+CFG (zero-shot)96.6Stay on topic with Classifier-Free Guidance-
LLaMA-30B+CFG (zero-shot)96.4Stay on topic with Classifier-Free Guidance-
LLaMA-13B+CFG (zero-shot)95.1Stay on topic with Classifier-Free Guidance-
0 of 3 row(s) selected.