Run Llama 3 on Windows | Build with Meta Llama

Navyata Bawa from Meta will showcase how to run Llama on Windows using Hugging Face APIs. The video will share a step-by-step tutorial using the Hugging Face Transformers library, and running inference using the Llama 3 8B Instruct model.

# Timestamps
00:00 Introduction
00:48 Background and setup
01:22 Download model weights from Hugging Face
02:42 Install dependencies
03:37 Creating your example script
07:03 Log into Hugging Face and run the script
08:07 Links and resources

# Additional Resources

- - -

# Follow us on social media

[eyalpery]

Thank you for this video! It was very informative and I successfully managed to deploy it on my Windows 10 laptop.

[parvesh-rana]

Would like to see a video on fine-tuning

[aminaleali]

How about if you ZOOM in to the code so we can see it? No one can read 7 size font.

[____________________________.x]

Where do I find the minimum hardware requirements for each model?

[Patrickh]

Excellent video series… recommended also for high school STEM projects. They may need more “initial setup” videos on type of editor (e.g., Visual Studio, PyCharm, etc). Let’s get kids involved as well. 🙌😎

[rahul]

ive been getting invalid token passed even though i did get it from hugging face access token please help

[crowsnest]

The install should be a simple menu selection and thats it! who at meta is responsible for this convoluted install?

[maksymkyiv]

The power of creation is imagination, or 3D logic with memory and emotion.