thuanz123/enhancing-transformers

stage2 transformer

Mdahao opened this issue · 2 comments

          hi @manuelknott, the code for stage2 transformer is currently buggy so after I fixed everything, I will try to train and released a pretrained model. But this will be a long time later since I'm still learning about autoregressive modeling with transformers.

Originally posted by @thuanz123 in #8 (comment)

Hi, I'm sorry to bother you. Has this pre-trained model been released?

Hi, unfortunately, training the stage 2 model requires a large computational budget so that there will be no pretrained weight for stage 2 model. However, you can try to plug in other stage 2 model like VQ-Diffusion or MaskGIT, which is much more effficient to train

If you dont have any further question, I will close this issue. Feel free to re-open it and/or ask any more questions