All the articles with the tag "GPT".
An attempt to build a GPT-style LLM from scratch with PyTorch. Covers the full architecture, pre-training loop, decoding strategies, and loading OpenAI GPT-2 weights.
Chat with
Mike 3.0
Send a message to start the chat!
You can ask the bot anything about me and it will help to find the relevant information!
Try asking:
