📊 Showing 4 results | 📏 Metric: Accuracy (% )
| Rank | Model | Paper | Accuracy (% ) | Date | Code |
|---|---|---|---|---|---|
| 1 | LLaMA2-7b | QLoRA: Efficient Finetuning of Quantized LLMs | 82.63 | 2023-05-23 | 📦 qwenlm/qwen 📦 QwenLM/Qwen-7B 📦 artidoro/qlora |
| 2 | LLaMA2-7b | GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs | 82.63 | 2024-08-27 | 📦 On-Point-RND/GIFT_SW |
| 3 | LLaMA2-7b | DoRA: Weight-Decomposed Low-Rank Adaptation | 81.93 | 2024-02-14 | 📦 NVlabs/DoRA 📦 catid/dora 📦 seanzhang-zhichen/llama3-chinese 📦 nbasyl/DoRA 📦 ayyucedemirbas/DoRA |
| 4 | LLaMA2-7b | LoRA: Low-Rank Adaptation of Large Language Models | 80.28 | 2021-06-17 | 📦 labmlai/annotated_deep_learning_paper_implementations 📦 hiyouga/llama-efficient-tuning 📦 tatsu-lab/stanford_alpaca |