List your company
ResearchFormerly WizWand

General NLP Evaluation on Natural Language Benchmarks Aggregate

62.31Average ScoreDense
23.746833.758443.7753.7816Mar 6, 2024
Updated 8mo ago

Evaluation results

MethodLinks
DenseLLM=Baichuan2-13B, Ratio=0.00%2024.0362.31100
DenseLLM=Baichuan2-7B, Ratio=0.00%2024.0357.67100
DenseLLM=Llama2-13B, Ratio=0.00%2024.0355.14100
ShortGPTLLM=Baichuan2-13B, Ratio=24.7%2024.0354.4387.35
LaCoLLM=Baichuan2-13B, Ratio=24.7%2024.0353.4385.75
ShortGPTLLM=Llama2-13B, Ratio=24.6%2024.0350.5391.64
RWKV-7BBackbone=RWKV-7B, Pruning ratio=0%2024.0350.37100
ShortGPTLLM=Baichuan2-7B, Ratio=24.2%2024.0349.0885.1
DenseLLM=Llama2-7B, Ratio=0.00%2024.0347.78100
LaCoLLM=Llama2-13B, Ratio=24.6%2024.0347.6286.36
ShortGPTBackbone=RWKV-7B, Pruning ratio=9.4%2024.0343.9487.23
LaCoLLM=Baichuan2-7B, Ratio=24.2%2024.0342.9374.44
LLMPrun.LLM=Baichuan2-7B, Ratio=24.2%2024.0341.7672.41
ShortGPTLLM=Llama2-7B, Ratio=27.1%2024.0341.2486.31
Mamba-2.8BBackbone=Mamba-2.8B, Pruning ratio=0%2024.0341.12100
ShortGPTBackbone=RWKV-7B, Pruning ratio=18.8%2024.0340.3880.17
LLMPrun.LLM=Baichuan2-13B, Ratio=24.3%2024.0339.262.91
ShortGPTBackbone=Mamba-2.8B, Pruning ratio=10.9%2024.0339.0895.04
LLMPrun.LLM=Llama2-13B, Ratio=24.4%2024.0338.9770.67
LaCoLLM=Llama2-7B, Ratio=27.1%2024.0338.4180.39
ShortGPTBackbone=Mamba-2.8B, Pruning ratio=20.3%2024.0338.3693.29
ShortGPTBackbone=Mamba-2.8B, Pruning ratio=25%2024.0337.1890.42
ShortGPTBackbone=RWKV-7B, Pruning ratio=25%2024.0336.8573.16
ShortGPTBackbone=Mamba-2.8B, Pruning ratio=31.3%2024.0335.5986.55
SliceGPTLLM=Llama2-13B, Ratio=23.6%2024.0334.8563.2
LLMPrun.LLM=Llama2-7B, Ratio=27.0%2024.0334.7872.79
ShortGPTBackbone=RWKV-7B, Pruning ratio=28.1%2024.0333.8267.14
SliceGPTLLM=Llama2-7B, Ratio=26.4%2024.0332.8468.73
SliceGPTLLM=Baichuan2-7B, Ratio=22.2%2024.0326.2345.48
SliceGPTLLM=Baichuan2-13B, Ratio=22.8%2024.0325.2340.49