nanochat - Andrej Karpathy's full endtoend ChatGPT iteration is avaliable as a raw transformer checkpoint but as a HF compatible safetensor file as well

Leveraging the 5.0dev HF transformer some compatibility is avaliable, but a GGUF conversion fails because the model's format is not (yet) known

Would be great if that model would be supported so it can benefit from the llama.cpp ecosystem ?

nanochat-torchinfo-keras.txt