parameter-efficient fine-tuning on HellaSwag

Metric: Accuracy (% ) (higher is better)

LeaderboardDataset
Loading chart...
#ModelAccuracy (% )AugmentationsPaperDateCode
1LLaMA2-7b76.68YesGIFT-SW: Gaussian noise Injected Fine-Tuning of ...2024-08-27Code
2LLaMA2-7b76.67YesLoRA: Low-Rank Adaptation of Large Language Models2021-06-17Code
3LLaMA2-7b76.27YesDoRA: Weight-Decomposed Low-Rank Adaptation2024-02-14Code