Hi, everyone I just started programming GPT model almost all by myself after some patches it started working and now I’m worried that my layers are not connected as they should be, in the visualization(which I will upload) I can recognize some things like multi-head and linear layer, but I still think that something is messed up(please don’t hate me if something is wrong, I’m just someone who codes as a hobby)
1 Like
This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.