Quick and dirty chatbot implementation using LLaMA 7B inspired by George Hotz tinygrad example.
See https://github.com/juncongmoo/pyllama for information on accessing the weights and post-training quantization.
Quick and dirty chatbot implementation using LLaMA 7B inspired by George Hotz tinygrad example.
See https://github.com/juncongmoo/pyllama for information on accessing the weights and post-training quantization.