Berkan Ottlik@berkott3Jul 18, 2023If your loss ever looks like this, it might be because you aren't calling optimizer.zero_grad() in PyTorch!!! Learned this the hard way lol.2100
Berkan Ottlik@berkott3Jun 14, 2023Is the human race just running gradient descent on a mass scale?151
Berkan Ottlik@berkott3May 18, 2023Anyone know alternatives to @modal_labs that you can run on your own hardware/VPC?41
Berkan Ottlik@berkott3Apr 27, 2023Why does the login to ChatGPT suck and take so long? Bard and HuggingChat are so much better in that respect, which is why I sometimes default to them.11120
Berkan Ottlik@berkott3Jan 4, 2023Yet another blog about transformers: berkan.xyz/posts/2023/01/… (except it's written by me and I think it's decent 😊)348
