MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers
Paper
•
2212.07841
•
Published
Paper: https://arxiv.org/abs/2212.07841.
Code: https://github.com/microsoft/SimXNS/tree/main/MASTER.
This is the checkpoint after pretraining on the MS-MARCO corpus. You may use this checkpoint as the initialization for finetuning.
To load this checkpoint for initialization, you may follow:
from transformers import AutoModel
model = AutoModel.from_pretrained('lx865712528/master-base-pretrained-msmarco')