%% Title: LLaMA Created: 2023-05-12 12:23 Status: Parent: [[Resources/Computing/AIML/Systems|Systems]] Tags: Source: %% # LLaMA A [[Resources/Computing/AIML/LargeLanguageModel|LargeLanguageModel]] developed by Meta. - [ggeranov/llama.cpp](https://github.com/ggerganov/llama.cpp) is a port of the original software to run on commodity hardware. - [A comprehensive guide to running Llama 2 locally](https://replicate.com/blog/run-llama-locally) - [Llama 3 in pure numpy](https://docs.likejazz.com/llama3.np/) - [Optimizing llama energy efficiency](https://jacquesmattheij.com/llama-energy-efficiency/) - [Using Llamafiles for Embeddings in Local RAG Applications](https://future.mozilla.org/news/llamafiles-for-embeddings-in-local-rag-applications/)