Victoriaheiheihei
Victoriaheiheihei
你好请问使用的数据集在哪里说明了啊？我也想跑一个自己的模型
还有一个问题，按照我的理解如果使用retromae预训练的模型初始化reranker也是可以的吧，当时是出于什么因素考量选择了xlm-deberta-base呢
感谢！ 此外还有一个问题，为什么之前retromae reranker选择了deberta，现在bge选择了xlm-deberta，为什么不在retromae预训练模型的基础上训练一个reranker而选择其他模型初始化呢？
似乎偏好数据集不支持这个格式
哈喽， 请问你安装上了吗？我为什么安装的时候安装到pytrec_eval总会报错呢
请问这个template有哪些可选项啊，需要自己写吗？
Same issue occured on the book corpus. Considering the bookcorpus has been private,where can i get similar dataset? Should I crawl from scratch?
Thank you for your reply! I tried to finetune the ANCE model (using the hard_negs.txt on [Shitao/RetroMAE_MSMARCO](https://huggingface.co/Shitao/RetroMAE_MSMARCO)),but the results is lower than the reported one. Do you finetune the ANCE...
Thank you. I will try again
hello， It's a impressive work. I've got some confusion about evaluation process. I found that evaluation on test data was provided, but the test data didn't have any gold answers...