Lounis Hamroun·Sep 3I Rebuilt GPT-2 From Scratch. Then I Tried to Prove It Was CorrectWhat causal masking, weight layouts, floating-point errors, broken tests, and 12 Transformer blocks taught me about building models I can…A response icon3A response icon3
Awesomecreater·Aug 17I Taught Myself How GPT-2 Actually Thinks — By Building One From ScratchA few weeks ago I decided I was tired of using transformers without really understanding what’s happening inside one. Not the “attention is…
pdawg·Jul 16How to implement GPT-2 from scratch like KarpathyI spent two hours watching Andrej Karpathy build GPT from scratch, nodding along like it was clicking. Then I opened a blank file to build…A response icon1A response icon1
Seven Sky Tech·Jun 18I Tested 10 Best ChatGPT Image Prompts that Went Viral (2026)Mastering Trending ChatGPT Image Prompts with Examples to Create Stunning AI Art in MinutesA response icon1A response icon1
Andrey Lukyanenko·Jun 9Book Review: 50 ML Projects to Understand LLMsA review of Mike X Cohen's 50 ML Projects To Understand LLMs, a hands-on book that uses code, statistics, and controlled experiments to…A response icon1A response icon1
Sanyam·May 19I Built GPT-2 from Scratch in PyTorchGPT : Generative Pre-trained Transformer is a decoder-only transformer architecture which takes the tokens as input and predicts the next…
Syed Sarim Ahsan·May 14Building a GPT-2 Inference Engine From ScratchAfter building projects with HuggingFace and calling generate(), I realized I had no idea what was actually happening inside. So I built a…
Aranya Ray·Apr 3Micro-GPT2 — Building GPT-2 (124M) from Scratch in PyTorchEver wondered what actually happens inside GPT-2 — the model that kicked off the modern era of large language models?
