From Zero to 250M: How I Built the STE Dataset to Train a Tiny LLM from Scratch
The story of building a Simple Thoughts Experiments (STE) dataset from scratch.
13 min read
FeaturedLLMGenerative AI
All TopicsRead From Zero to 250M: How I Built the STE Dataset to Train a Tiny LLM from Scratch
Generative AI
1 post with this topic