List your company

General Reasoning and Coding on Key-Value Recall Non-Factoid

64.1GSM8K AccuracyREMIX (Random / -)
10.74824.59938.4552.301Nov 11, 2024

Evaluation results

MethodLinks
REMIX (Random / -)Backbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=Random / -2024.1164.175.985.37589.177.9
REMIX (K-Pile / -)Backbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=K-Pile / -2024.1147.358.462.21974.352.2
REMIX (Random / K-Pile)Backbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=Random / K-Pile2024.1145.845.474.751.286.860.8
No MixingBackbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=No Mixing2024.1124.427.349.526.766.638.9
REMIX (- / Random)Backbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=- / Random2024.1115.111.733.816.566.828.8
REMIX (- / K-Pile)Backbone=Llama-3-8B, Mixing Strategy (DM1 / DM2)=- / K-Pile2024.1112.88.840.516.870.229.8