Language Modeling on Perplexity Evaluation Dataset
14.13PPLDense
Evaluation results
| Method | Links | |
|---|---|---|
| DensePrune%=0%, Model=LLaMA-3-8B, Evaluation Protocol=Zero-shot2025.12 | 14.13 | |
| Token FilteringPrune%=20%, Model=LLaMA-3-8B, Evaluation Protocol=Zero-shot2025.12 | 19.46 | |
| PPPrune%=20%, Model=LLaMA-3-8B, Evaluation Protocol=Zero-shot2025.12 | 20.56 | |
| FLAPPrune%=20%, Model=LLaMA-3-8B, Evaluation Protocol=Zero-shot2025.12 | 23.25 | |
| SlimGPT w/oPrune%=20%, Model=LLaMA-3-8B, Evaluation Protocol=Zero-shot2025.12 | 32.79 | |
| FLAPPrune%=50%, Model=LLaMA-3-8B, Evaluation Protocol=Zero-shot2025.12 | 63.33 | |
| Token FilteringPrune%=50%, Model=LLaMA-3-8B, Evaluation Protocol=Zero-shot2025.12 | 74.62 | |
| SlimGPT w/oPrune%=50%, Model=LLaMA-3-8B, Evaluation Protocol=Zero-shot2025.12 | 85.32 | |
| PPPrune%=50%, Model=LLaMA-3-8B, Evaluation Protocol=Zero-shot2025.12 | 104.01 |