A quick refresher on the maths behind LLMs: vectors, matrices, projections, embeddings, logits and softmax.| Giles' Blog
Right now, starting a debugging session using AI before googling can leave you stuck, especially with newer technologies| Giles' Blog
Batching speeds up training and inference, but for LLMs we can't just use matrices for it -- we need higher-order tensors.| Giles' Blog
Moving on from a toy self-attention mechanism, it's time to find out how to build a real trainable one. Following Sebastian Raschka's book 'Build a Large Language Model (from Scratch)'. Part 8/??| Giles' Blog
How we actually do matrix operations for neural networks in frameworks like PyTorch. For ML beginners.| Giles' Blog
Archive of Giles Thomas’s blog posts from February 2025. Insights on AI, startups, and software development, plus occasional personal reflections.| www.gilesthomas.com