minGPT

minGPT

karpathy/minGPT

A PyTorch re-implementation of GPT training. minGPT tries to be small, clean, interpretable and educational, as most of the currently available ones are a bit sprawling. GPT is not a complicated model and this implementation is appropriately about 300 lines of code, including boilerplate and a totally unnecessary custom causal self-attention module…

Source: github.com/karpathy/minGPT

Subscribe to our Digest