Meta's Llama-3.1-8B Model with FastAPI

This repository contains code to run Meta's Llama-3.1-8B model locally using FastAPI. The model is obtained from Hugging Face.

• I code this while learning the concepts , and how to use it.

How to Run Locally

1. Clone this repository to your local machine.
2. Install the required dependencies by running pip install -r requirements.txt.
3. Run the FastAPI server by executing uvicorn main:app --reload.
4. You can now access the API at http://localhost:8000.

References

• Hugging Face
• FastAPI
• YouTube tutorials for learning how to run models locally.

Feel free to explore and modify the code as needed. Enjoy running Meta's Llama model locally!