Carlos Lassance

Results 3 comments of Carlos Lassance

Hi @kuro96al, we pretrained the model from scratch using the japanese Mr.TyDi corpus (https://github.com/castorini/mr.tydi), we then trained with a contrastive loss using japanese MMARCO (https://github.com/unicamp-dl/mMARCO) and finally finetuned with the...

> Thank you for your response. Is the pre-trained model uploaded on platforms like Hugging Face? Unfortunately it is not, not sure if we still have it... > We attempted...

Hey Joel, So at the time I think I basically tokenized everything (without taking the time into account) and then ran it a query at the time with a single...