1
The Fourier transform is a neural network
The site of Sid
The site of Sid
Visit sidsite.com → RSS feedOn Hacker News Mar 2019 – Jun 2023
AI & Machine Learning 3Software Engineering 2Math & Algorithms 1Life, Learning & Writing 1
The site of Sid
I trained a BERT model (Devlin et al, 2019) from scratch on my desktop PC (which has a Nvidia 3060 Ti 8GB GPU). The model architecture, tokenizer, and trainer all came from Hugging Face libraries, and my contribution was mainly setting up the code, setting up the data (~20GB uncompressed text), and leaving my computer…
The site of Sid
The site of Sid