LLaMA & Alpaca: “ChatGPT” On Your Local Computer 🤯 | Tutorial

"how you can run state-of-the-art large language models on your local computer" using two models which are "comparable or even outperform GPT [but can] run on your local computer... released under a non-commercial license":

• "dalai library" - allows us to run LLaMA & Alpaca, provides an API
• "LLaMA: foundational (or broad) language model ... 13x smaller than GPT-3 [but] outperforms [it] on most benchmarks.... LLaMA-7B takes up around 31GB ... trained primarily on English
• Alpaca model: fine-tuned LLaMA capable of following instructions" like ChatGPT, about 4 GB.

From a followup Q&A:

• training these models with your own data: " Stanford released the data used, the code for generating the instruction-following data and the code for fine-tuning the LLaMA model... the documentation is very well written... check out the Alpaca-LoRA repository... if you want to fine-tune the model on your own (single) GPU ... [as it] uses low-rank adaption (LoRA) ... parameter-efficient fine-tuning technique...
• LLaMA model's input & output token limit: 2048 tokens
• to get code, use a non-quantized version of Alpaca on a GPU
• the models cannot access the internet and dont learn, but do remember interactions within a single session.