Search results

Parameters are not shared in experts

Status: Open.

#6 In SimiaoZuo/MoEBERT;

· tairan-w opened on Oct 2, 2022

What is the bash script of finetune without MoE

Status: Open.

#5 In SimiaoZuo/MoEBERT;

· CaffreyR opened on Aug 17, 2022

Error when run bash bert_base_mnli_example.sh

Status: Open.

#4 In SimiaoZuo/MoEBERT;

· CaffreyR opened on Aug 17, 2022

How about the performance difference between token-gate and sentence gate?

Status: Open.

#3 In SimiaoZuo/MoEBERT;

· GeneZC opened on Jun 3, 2022

"Need to turn the model to a MoE first" error

Status: Open.

#2 In SimiaoZuo/MoEBERT;

· Harry-zzh opened on May 10, 2022