Multitask Language Understanding on TMLU
37.17AccuracyDense
Evaluation results
| Method | Links | |
|---|---|---|
| DenseBase Model=DeepSeek-7B, Sparsity=Dense, Evaluation Protocol=Zero-shot2025.06 | 37.17 | |
| DenseBase Model=LLaMA-2-7B, Sparsity=Dense, Evaluation Protocol=Zero-shot2025.06 | 29.58 | |
| SparsegptBase Model=DeepSeek-7B, Sparsity=2:4, Evaluation Protocol=Zero-shot2025.06 | 25.99 | |
| MaskProBase Model=LLaMA-2-7B, Sparsity=2:4, Evaluation Protocol=Zero-shot2025.06 | 25.38 | |
| MaskProBase Model=DeepSeek-7B, Sparsity=2:4, Evaluation Protocol=Zero-shot2025.06 | 25.37 | |
| Pruner-ZBase Model=LLaMA-2-7B, Sparsity=2:4, Evaluation Protocol=Zero-shot2025.06 | 25.13 | |
| SparsegptBase Model=LLaMA-2-7B, Sparsity=2:4, Evaluation Protocol=Zero-shot2025.06 | 25.03 | |
| Pruner-ZBase Model=DeepSeek-7B, Sparsity=2:4, Evaluation Protocol=Zero-shot2025.06 | 24.36 |