casinca/LLM-quest

Verbose implementations of LLMs architectures, techniques and research papers from scratch. DeepSeek, Qwen3..., RLHF, MoE, Multimodal...

37
/ 100
Emerging

This project offers detailed, from-scratch implementations of various large language model (LLM) architectures and advanced techniques. It provides a transparent view of how complex LLMs like DeepSeek, Qwen3, and Gemma are built, along with methods for alignment (like RLHF) and multimodal capabilities. The resource is invaluable for AI researchers, machine learning engineers, and students who want to understand, experiment with, and learn the intricate mechanics behind state-of-the-art LLMs.

Use this if you are an AI researcher or machine learning engineer looking to deeply understand, reverse-engineer, and experiment with the internal workings of modern LLMs and their underlying techniques from first principles.

Not ideal if you are looking for an out-of-the-box LLM to use in an application, or if you need a high-level library for rapid prototyping without delving into the architectural details.

AI-research LLM-architecture machine-learning-engineering deep-learning AI-education
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/casinca/LLM-quest"

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