In this video I will show you the key features of the Llama 3 model and how you can run the Llama 3 model on your own computer. First, I will cover Meta's blog post in detail to explain what's new about the Llama 3 model, and then I will show you how to run the Llama 3 model on your own computer in a very simple way. To do this, we will use the vLLM and Gradio libraries, which will allow us to interact with the Llama 3 model in a visually appealing and lightningfast way. I hope you'll enjoy how easy it actually is! Let me know in the comments what you think about the new Llama 3 model. :)
My Medium Article for This Video:
/ 1f533e9abff7
Github Repository
https://github.com/thisserand/llama3_...
Request Access To Llama 3
https://llama.meta.com/llamadownloads/
Llama 3 Blog Post
https://ai.meta.com/blog/metallama3/
My Workstation
GPU: NVIDIA RTX 6000 Ada https://nvda.ws/47U7wmA
CPU: Intel Core i913900K https://amzn.to/47qDQgp
RAM: Corsair Vengeance 64 GB https://amzn.to/47o4S8e
Motherboard: ASRock Z790M PG https://amzn.to/3SxvtLS
Storage: Samsung 980 PRO 2 TB https://amzn.to/3u8X23Y
PSU: Corsair RM 850x https://amzn.to/3uhTNXS
Case: Fractal Design Meshify 2 Mini https://www.fractaldesign.com/produc...
CPU Cooler: Noctua NHU12A https://amzn.to/3Qpv4IM
Case Fan: Noctua NFA12x25 https://amzn.to/3srf1lE
Web Highlights Chrome Extension
https://bit.ly/3Wa8KXX
00:00:00 Intro
00:00:20 Key Changes
00:01:55 Meta Blog Post
00:04:13 Model Architecture
00:06:43 Training Data
00:08:00 Scaling Up PreTraining
00:10:13 Instruction FineTuning
00:12:02 400B+ Model Is Coming
00:14:03 Llama 3 On Your Local Computer
Stay in Touch
Medium
/ martinthissen
LinkedIn
/ mthissen135
YouTube
Of course, feel free to subscribe to my channel! :)
Of course, financial support is completely voluntary, but I was asked for it:
/ martinthissen
https://kofi.com/martinthissen