In this video I will show you how you can run state-of-the-art large language models on your local computer. Yes, you’ve heard right. For this we will use the Dalai library which allows us to run the foundational language model LLaMA as well as the instruction-following Alpaca model. While the LLaMA model is a foundational (or broad) language model that is able to predict the next token (word) based on a given input sequence (sentence), the Alpaca model is a fine-tuned version of the LLaMA model capable of following instructions (which you can think of as ChatGPT behaviour). What’s even more impressive, both these models achieve comparable results or even outperform their GPT counterparts while still being small enough to run on your local computer. In this video I will show you that it only takes a few steps (thanks to the Dalai library) to run “ChatGPT” on your local computer.
00:00:00 Intro
00:00:30 LLaMA Model
00:03:54 Dalai Library Prerequisites
00:06:04 Setup Dalai & LLaMA
00:08:39 Alpaca Model
00:10:57 Setup Dalai & Alpaca
00:12:50 Outro
My Medium Article for This Video:
Dalai GitHub Repository:
LLaMA Weird Character Generation Issue:
Helpful LLaMA prompts:
Resources:
AI Explained YT Video:
Self-Instruct:
Ark Forecast:
Alpaca:
Dalai:
Introducing LLaMA:
LLaMA Paper:
Stay in Touch
Medium
YouTube
Of course, feel free to subscribe to my channel! 🙂
(of course, financial support is completely voluntary, but I was asked for this)