Jokin Labaien issues

Repositories
Issues
Comments

Results 3 issues of


                                            Jokin Labaien

DiCE on time-series data

Hi, I was wondering if DiCE works with continuous variables such as time-series data or not.

Pretrained models with RADIX > 2 and K > 1

Are you planning to upload pretrained models with RADIX higher than 2 and with higher cardinality? Thanks in advance.

Using sparsegen for attention probabilities

Hi! I'm trying to use these sparse functions as an alternative to the softmax function in the attention mechanisms of transformers. However, the loss becomes NaN in the first iteration......