Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
Open paper
Benchmark
Model
Rank
Results
sentence-completion-on-hellaswag
Debias-SparseGPT (Mistral7B-v0.3-IT,1:4 sparse)
#152
Accuracy: 59.72
Rank counts only results with a code link.