List your company

Zero-shot Classification on EleutherAI (test)

64.7AccuracyWanda + SparseSwaps
46.08450.91755.7560.583Dec 11, 2025

Evaluation results

MethodLinks
Wanda + SparseSwapsModel=GEMMA-2 9B, Sparsity=2:42025.1264.7
RIA + SparseSwapsModel=GEMMA-2 9B, Sparsity=2:42025.1264.6
RIA + DSnoTModel=GEMMA-2 9B, Sparsity=60%2025.1264.43
RIAModel=GEMMA-2 9B, Sparsity=60%2025.1264.37
RIA + SparseSwapsModel=GEMMA-2 9B, Sparsity=60%2025.1264.32
RIA + DSnoTModel=GEMMA-2 9B, Sparsity=2:42025.1264.17
RIAModel=GEMMA-2 9B, Sparsity=2:42025.1263.87
Wanda + SparseSwapsModel=GEMMA-2 9B, Sparsity=60%2025.1263.84
WandaModel=GEMMA-2 9B, Sparsity=2:42025.1263.73
Wanda + DSnoTModel=GEMMA-2 9B, Sparsity=2:42025.1263.66
Wanda + DSnoTModel=GEMMA-2 9B, Sparsity=60%2025.1263.49
WandaModel=GEMMA-2 9B, Sparsity=60%2025.1263.39
RIA + SparseSwapsModel=QWEN2.5 7B, Sparsity=60%2025.1261.22
RIA + SparseSwapsModel=QWEN2.5 7B, Sparsity=2:42025.1260.31
Wanda + SparseSwapsModel=QWEN2.5 7B, Sparsity=60%2025.1260.15
Wanda + SparseSwapsModel=QWEN2.5 7B, Sparsity=2:42025.1259.92
RIAModel=QWEN2.5 7B, Sparsity=60%2025.1259.84
RIA + DSnoTModel=QWEN2.5 7B, Sparsity=60%2025.1259.81
RIA + DSnoTModel=QWEN2.5 7B, Sparsity=2:42025.1259.72
WandaModel=QWEN2.5 7B, Sparsity=2:42025.1259.52
WandaModel=QWEN2.5 7B, Sparsity=60%2025.1259.26
Wanda + DSnoTModel=QWEN2.5 7B, Sparsity=60%2025.1259.26
Wanda + DSnoTModel=QWEN2.5 7B, Sparsity=2:42025.1259.09
RIAModel=QWEN2.5 7B, Sparsity=2:42025.1258.66
Wanda + SparseSwapsModel=YI-1.5 9B, Sparsity=60%2025.1254.84
RIA + SparseSwapsModel=YI-1.5 9B, Sparsity=60%2025.1254.45
Wanda + DSnoTModel=YI-1.5 9B, Sparsity=60%2025.1253.79
WandaModel=YI-1.5 9B, Sparsity=60%2025.1253.59
RIA + DSnoTModel=YI-1.5 9B, Sparsity=60%2025.1252.96
RIAModel=YI-1.5 9B, Sparsity=60%2025.1252.81
RIAModel=YI-1.5 9B, Sparsity=2:42025.1252.68
WandaModel=YI-1.5 9B, Sparsity=2:42025.1252.58
Wanda + SparseSwapsModel=YI-1.5 9B, Sparsity=2:42025.1252.43
RIA + SparseSwapsModel=YI-1.5 9B, Sparsity=2:42025.1252.3
Wanda + DSnoTModel=YI-1.5 9B, Sparsity=2:42025.1252.16
RIA + SparseSwapsModel=DEEPSEEK 7B, Sparsity=60%2025.1251.47
RIA + SparseSwapsModel=DEEPSEEK 7B, Sparsity=2:42025.1251.46
RIA + DSnoTModel=YI-1.5 9B, Sparsity=2:42025.1251.36
RIAModel=DEEPSEEK 7B, Sparsity=2:42025.1251.22
Wanda + SparseSwapsModel=DEEPSEEK 7B, Sparsity=60%2025.1251.02
RIA + SparseSwapsModel=LLAMA-3.1 8B, Sparsity=60%2025.1251.02
WandaModel=DEEPSEEK 7B, Sparsity=2:42025.1251.02
RIAModel=DEEPSEEK 7B, Sparsity=60%2025.1250.92
RIA + DSnoTModel=DEEPSEEK 7B, Sparsity=60%2025.1250.83
Wanda + SparseSwapsModel=LLAMA-3.1 8B, Sparsity=60%2025.1250.78
Wanda + DSnoTModel=DEEPSEEK 7B, Sparsity=2:42025.1250.78
Wanda + DSnoTModel=DEEPSEEK 7B, Sparsity=60%2025.1250.75
WandaModel=DEEPSEEK 7B, Sparsity=60%2025.1250.74
Wanda + SparseSwapsModel=DEEPSEEK 7B, Sparsity=2:42025.1250.36
RIA + SparseSwapsModel=LLAMA-3.1 8B, Sparsity=2:42025.1249.9
RIA + DSnoTModel=DEEPSEEK 7B, Sparsity=2:42025.1249.86
RIAModel=LLAMA-3.1 8B, Sparsity=60%2025.1249.56
RIA + DSnoTModel=LLAMA-3.1 8B, Sparsity=60%2025.1249.56
Wanda + SparseSwapsModel=LLAMA-3.1 8B, Sparsity=2:42025.1248.83
WandaModel=LLAMA-3.1 8B, Sparsity=60%2025.1248.18
Wanda + DSnoTModel=LLAMA-3.1 8B, Sparsity=60%2025.1248.18
RIAModel=LLAMA-3.1 8B, Sparsity=2:42025.1247.87
RIA + DSnoTModel=LLAMA-3.1 8B, Sparsity=2:42025.1247.13
Wanda + DSnoTModel=LLAMA-3.1 8B, Sparsity=2:42025.1247.01
WandaModel=LLAMA-3.1 8B, Sparsity=2:42025.1246.8