Language Modeling on Perplexity Evaluation (zero-shot)
10.98PPL (zero-shot)Dense
Evaluation Results
| Method | Links | |
|---|---|---|
| DensePruning Ratio=0%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 10.98 | |
| PPPruning Ratio=20%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 12.52 | |
| PPPruning Ratio=25%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 13.32 | |
| Token FilteringPruning Ratio=20%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 13.37 | |
| SlimGPT w/oPruning Ratio=20%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 13.8 | |
| FLAPPruning Ratio=20%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 14.13 | |
| Token FilteringPruning Ratio=25%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 14.69 | |
| SlimGPT w/oPruning Ratio=25%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 15.1 | |
| FLAPPruning Ratio=25%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 15.49 | |
| PPPruning Ratio=33%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 15.83 | |
| Token FilteringPruning Ratio=33%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 16.39 | |
| FLAPPruning Ratio=33%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 17.79 | |
| SlimGPT w/oPruning Ratio=33%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 18.11 | |
| PPPruning Ratio=50%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 28.86 | |
| Token FilteringPruning Ratio=50%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 29.22 | |
| FLAPPruning Ratio=50%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 29.45 | |
| SlimGPT w/oPruning Ratio=50%, Base Model=LLaMA-2-13B, Zero-shot=true2025.12 | 32.67 |