Technology Radar
Published : Apr 26, 2023
NOT ON THE CURRENT EDITION
This blip is not on the current edition of the Radar. If it was on one of the last few editions, it is likely that it is still relevant. If the blip is older, it might no longer be relevant and our assessment might be different today. Unfortunately, we simply don't have the bandwidth to continuously review blips from previous editions of the Radar.
Understand more
Apr 2023
Assess
nanoGPT es un framework para entrenamiento y fine-tuning de transformadores generativos preentrenados de tamaño medio (GPT). El autor, Andrej Karpathy, hace referencia a las publicaciones Attention is All You Need y OpenAI's GPT-3 para construir un GPT desde cero usando PyTorch. Con todo el revuelo en torno a la IA generativa, queremos destacar nanoGPT por su simplicidad y enfoque en articular claramente los componentes básicos de la arquitectura GPT.