List your company

General Reasoning and Coding on PopQA Non-Factoid

51.4GSM8K AccuracyREMIX (Random / -)
15.41624.75834.143.442Nov 11, 2024

Evaluation results

MethodLinks
REMIX (Random / -)Backbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=Random / -2024.1151.489.382.781.86672.2
REMIX (K-Pile / -)Backbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=K-Pile / -2024.1146.492.79487.290.982.2
REMIX (Random / K-Pile)Backbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=Random / K-Pile2024.1138.588.788.379.274.473.8
REMIX (- / K-Pile)Backbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=- / K-Pile2024.1125.99492.473.974.772.2
No MixingBackbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=No Mixing2024.111992.47755.148.558.4
REMIX (- / Random)Backbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=- / Random2024.1116.893.587.559.370.765.6