List your company

Text Generation on WikiText-2

4.88PerplexityFP16
3.425613.242823.0632.8772Oct 16, 2024Dec 16, 2024Feb 16, 2025Apr 18, 2025Jun 19, 2025Aug 19, 2025Oct 20, 2025

Evaluation results

MethodLinks
FP16Avg. Bit=16, Backbone=LLaMA2-13B2024.104.88
VPTQAvg. Bit=4, Backbone=LLaMA2-13B2024.104.96
AWQAvg. Bit=4, Backbone=LLaMA2-13B2024.104.98
LLM-MQAvg. Bit=4, Backbone=LLaMA2-13B2024.104.98
CMPQAvg. Bit=4, Backbone=LLaMA2-13B2024.104.98
QuIP#Avg. Bit=4, Backbone=LLaMA2-13B2024.105
GPTQAvg. Bit=4, Backbone=LLaMA2-13B2024.105.08
RTNAvg. Bit=4, Backbone=LLaMA2-13B2024.105.2
QuIPAvg. Bit=4, Backbone=LLaMA2-13B2024.105.29
AWQAvg. Bit=3, Backbone=LLaMA2-13B2024.105.32
QuIP#Avg. Bit=3, Backbone=LLaMA2-13B2024.105.34
CMPQAvg. Bit=3, Backbone=LLaMA2-13B2024.105.34
GPTVQAvg. Bit=3, Backbone=LLaMA2-13B2024.105.41
VPTQAvg. Bit=3, Backbone=LLaMA2-13B2024.105.42
FP16Avg. Bit=16, Backbone=LLaMA2-7B2024.105.47
CMPQAvg. Bit=4, Backbone=LLaMA2-7B2024.105.61
VPTQAvg. Bit=4, Backbone=LLaMA2-7B2024.105.64
QuIPAvg. Bit=3, Backbone=LLaMA2-13B2024.105.65
QuIP#Avg. Bit=4, Backbone=LLaMA2-7B2024.105.66
GPTVQAvg. Bit=4, Backbone=LLaMA2-7B2024.105.68
GPTVQAvg. Bit=4, Backbone=LLaMA2-13B2024.105.68
LLM-MQAvg. Bit=4, Backbone=LLaMA2-7B2024.105.68
GPTQAvg. Bit=4, Backbone=LLaMA2-7B2024.105.72
AWQAvg. Bit=4, Backbone=LLaMA2-7B2024.105.72
QuIPAvg. Bit=4, Backbone=LLaMA2-7B2024.105.72
LLM-MQAvg. Bit=3, Backbone=LLaMA2-13B2024.105.89
RTNAvg. Bit=4, Backbone=LLaMA2-7B2024.106.12
CMPQAvg. Bit=3, Backbone=LLaMA2-7B2024.106.14
GPTQAvg. Bit=3, Backbone=LLaMA2-13B2024.106.17
VPTQAvg. Bit=3, Backbone=LLaMA2-7B2024.106.17
QuIP#Avg. Bit=3, Backbone=LLaMA2-7B2024.106.19
GPTVQAvg. Bit=3, Backbone=LLaMA2-7B2024.106.19
AWQAvg. Bit=3, Backbone=LLaMA2-7B2024.106.24
GPTQAvg. Bit=3, Backbone=LLaMA2-7B2024.106.25
QuIPAvg. Bit=3, Backbone=LLaMA2-7B2024.106.8
LLM-MQAvg. Bit=3, Backbone=LLaMA2-7B2024.107.16
QuIP#Avg. Bit=2, Backbone=LLaMA2-13B2024.107.6
CMPQAvg. Bit=2, Backbone=LLaMA2-13B2024.109.14
QuIPAvg. Bit=2, Backbone=LLaMA2-13B2024.1010.09
RTNAvg. Bit=3, Backbone=LLaMA2-13B2024.1010.68
FP16Avg. Bit=16, Backbone=OPT-6.7B2024.1010.86
AWQAvg. Bit=4, Backbone=OPT-6.7B2024.1010.93
CMPQAvg. Bit=4, Backbone=OPT-6.7B2024.1010.95
DensePruning Ratio=0%, Backbone=Llama2-13B2025.1010.98
QuIPAvg. Bit=4, Backbone=OPT-6.7B2024.1010.98
LLM-MQAvg. Bit=4, Backbone=OPT-6.7B2024.1011.04
AWQAvg. Bit=3, Backbone=OPT-6.7B2024.1011.41
CMPQAvg. Bit=3, Backbone=OPT-6.7B2024.1011.45
GPTQAvg. Bit=4, Backbone=OPT-6.7B2024.1011.49
QuIPAvg. Bit=3, Backbone=OPT-6.7B2024.1011.51
RTNAvg. Bit=4, Backbone=OPT-6.7B2024.1012.15
DensePruning Ratio=0%, Backbone=Llama2-7B2025.1012.19
QuIP#Avg. Bit=2, Backbone=LLaMA2-7B2024.1012.3
FP16Avg. Bit=16, Backbone=OPT-2.7B2024.1012.47
CMPQAvg. Bit=4, Backbone=OPT-2.7B2024.1012.63
QuIPAvg. Bit=4, Backbone=OPT-2.7B2024.1012.69
AWQAvg. Bit=4, Backbone=OPT-2.7B2024.1012.73
GPTQAvg. Bit=4, Backbone=OPT-2.7B2024.1012.93
LLM-MQAvg. Bit=4, Backbone=OPT-2.7B2024.1013.06
CMPQAvg. Bit=3, Backbone=OPT-2.7B2024.1013.38
GPTQAvg. Bit=2, Backbone=LLaMA2-13B2024.1013.67
CMPQAvg. Bit=2, Backbone=LLaMA2-7B2024.1014.37
Wanda-spPruning Ratio=20%, Backbone=Llama2-13B2025.1014.64
OWLPruning Ratio=20%, Backbone=Llama2-13B2025.1014.76
GPTQAvg. Bit=3, Backbone=OPT-6.7B2024.1014.87
GISPPruning Ratio=20%, Backbone=Llama2-13B2025.1015.1
LLM-MQAvg. Bit=2, Backbone=LLaMA2-13B2024.1015.69
LLM-MQAvg. Bit=3, Backbone=OPT-6.7B2024.1016.01
AWQAvg. Bit=3, Backbone=OPT-2.7B2024.1016.32
RTNAvg. Bit=4, Backbone=OPT-2.7B2024.1016.69
FLAPPruning Ratio=20%, Backbone=Llama2-13B2025.1016.95
GISPPruning Ratio=20%, Backbone=Llama2-7B2025.1017.01
GPTQAvg. Bit=3, Backbone=OPT-2.7B2024.1017.09
QuIPAvg. Bit=3, Backbone=OPT-2.7B2024.1017.44
LLM-MQAvg. Bit=3, Backbone=OPT-2.7B2024.1018.09
CMPQAvg. Bit=2, Backbone=OPT-6.7B2024.1018.63
OWLPruning Ratio=30%, Backbone=Llama2-13B2025.1019.02
GISPPruning Ratio=30%, Backbone=Llama2-13B2025.1019.53
Wanda-spPruning Ratio=30%, Backbone=Llama2-13B2025.1019.73
ShortGPTPruning Ratio=20%, Backbone=Llama2-13B2025.1019.95
LLM-PrunerPruning Ratio=20%, Backbone=Llama2-13B2025.1019.99
FLAPPruning Ratio=30%, Backbone=Llama2-13B2025.1021.32
OWLPruning Ratio=20%, Backbone=Llama2-7B2025.1021.8
QuIPAvg. Bit=2, Backbone=OPT-6.7B2024.1022.33
Wanda-spPruning Ratio=20%, Backbone=Llama2-7B2025.1022.71
LLM-PrunerPruning Ratio=20%, Backbone=Llama2-7B2025.1024.25
GISPPruning Ratio=30%, Backbone=Llama2-7B2025.1024.27
GISPPruning Ratio=40%, Backbone=Llama2-13B2025.1026.56
QuIPAvg. Bit=2, Backbone=LLaMA2-7B2024.1027.12
LLM-PrunerPruning Ratio=30%, Backbone=Llama2-13B2025.1028.47
FLAPPruning Ratio=20%, Backbone=Llama2-7B2025.1029.19
OWLPruning Ratio=40%, Backbone=Llama2-13B2025.1031.13
CMPQAvg. Bit=2, Backbone=OPT-2.7B2024.1032.46
Wanda-spPruning Ratio=40%, Backbone=Llama2-13B2025.1032.91
GISPPruning Ratio=40%, Backbone=Llama2-7B2025.1034.54
OWLPruning Ratio=30%, Backbone=Llama2-7B2025.1034.64
Wanda-spPruning Ratio=30%, Backbone=Llama2-7B2025.1035.43
GPTQAvg. Bit=2, Backbone=LLaMA2-7B2024.1036.77
FLAPPruning Ratio=40%, Backbone=Llama2-13B2025.1037.76
LLM-PrunerPruning Ratio=30%, Backbone=Llama2-7B2025.1041.24