danielsobrado/llm_notebooks

Concepts and examples on using and training LLMs

30
/ 100
Emerging

This project offers a practical guide to working with Large Language Models (LLMs). It explains core concepts and demonstrates how to prepare and optimize these models for better performance. You'll learn how to convert an existing LLM into a more efficient format and reduce its size, making it faster and less resource-intensive to run locally. This is for anyone who wants to deploy or experiment with powerful language models like Llama or Vicuna on their own hardware.

No commits in the last 6 months.

Use this if you need to optimize existing large language models to run more efficiently on your local computer or server, especially when you're converting between different model formats.

Not ideal if you're looking for a simple drag-and-drop application for using LLMs without any technical setup or if you want to train a brand-new model from scratch without reference to existing architectures.

AI deployment Natural Language Processing model optimization local AI language model management
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

48

Forks

6

Language

Jupyter Notebook

License

Last pushed

Aug 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/danielsobrado/llm_notebooks"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.