Run Llama-2 Models Locally with llama.cpp

Llama is Meta’s answer to the growing demand for LLMs. Unlike its well-known technological relative, ChatGPT, Llama can run in full on under-specced machines, such as a MacBook Pros. This makes it a powerful tool for anything other major LLMs can do, as well as contemporary research and working with cutting-edge technologies. Drawing on the knowledge of experts across the industry with close knowledge of Meta’s powerful new tool, Llama Shortcuts will get you up and running with the three major iterations of Llama, working with third-party prompting tools, and diving into the awesome power of this locally hosted LLM. Individual shortcuts are brief and provide just the answer needed in the moment to harness the power of Llama.