Conversational Ability on Alpaca (test)
71.87Alpaca LC Win RateLoRA
Evaluation results
| Method | Links | |
|---|---|---|
| LoRABackbone Model=Deepseek R1-1.5B, Trainable Parameters=1.21M2025.12 | 71.87 | |
| FourierFTBackbone Model=Deepseek R1-1.5B, Trainable Parameters=0.15M2025.12 | 71.86 | |
| FAABackbone Model=Deepseek R1-1.5B, Trainable Parameters=1.63M2025.12 | 71.83 | |
| FFBackbone Model=Deepseek R1-1.5B, Trainable Parameters=1.5B2025.12 | 71.82 | |
| AdapterHBackbone Model=Deepseek R1-1.5B, Trainable Parameters=1.63M2025.12 | 71.81 | |
| FAABackbone Model=Qwen2 7B, Trainable Parameters=7.30M2025.12 | 33.88 | |
| FFBackbone Model=Qwen2 7B, Trainable Parameters=7.07B2025.12 | 33.72 | |
| AdapterHBackbone Model=Qwen2 7B, Trainable Parameters=7.29M2025.12 | 33.64 | |
| LoRABackbone Model=Qwen2 7B, Trainable Parameters=5.40M2025.12 | 33.62 | |
| FourierFTBackbone Model=Qwen2 7B, Trainable Parameters=0.85M2025.12 | 33.58 | |
| FAABackbone Model=LLaMA3 8B, Trainable Parameters=8.73M2025.12 | 30.1 | |
| FFBackbone Model=LLaMA3 8B, Trainable Parameters=8.03B2025.12 | 30.07 | |
| LoRABackbone Model=LLaMA3 8B, Trainable Parameters=6.47M2025.12 | 30.03 | |
| FourierFTBackbone Model=LLaMA3 8B, Trainable Parameters=0.91M2025.12 | 29.79 | |
| AdapterHBackbone Model=LLaMA3 8B, Trainable Parameters=8.73M2025.12 | 29.08 | |
| FAABackbone Model=LLaMA2 7B, Trainable Parameters=7.27M2025.12 | 10.92 | |
| LoRABackbone Model=LLaMA2 7B, Trainable Parameters=5.37M2025.12 | 10.89 | |
| FFBackbone Model=LLaMA2 7B, Trainable Parameters=6.94B2025.12 | 10.87 | |
| FourierFTBackbone Model=LLaMA2 7B, Trainable Parameters=0.82M2025.12 | 10.85 | |
| AdapterHBackbone Model=LLaMA2 7B, Trainable Parameters=7.27M2025.12 | 10.83 |