Large Language Models

Machine Learning

Artificial Intelligence

Llm Training

Explore recommended reads, summarized by AI

Training Infrastructure and Methods

Technical approaches to building and training large language models at scale.

Parallelization and Distributed Training

Sequence Processing and Prediction

Popular this week

QuarkAndCode

Supervised Fine-Tuning (SFT) for LLMs: Complete Guide

In

Level Up Coding

by

Khalid Salman

I built my own dual RTX 5090 AI workstation, and here’s what renting GPUs never taught me

Alex Chen

Using MinHash LSH to Find Near-Duplicate Training Data

In

Teradata Labs

by

Brandon Mincey

AI Training Checkpoint Storage: Why 128,000-GPU Clusters Break the Storage Stack

Nachiket Mehendale

Chinchilla Proved Bigger AI Models Were a Mistake

Latest stories

Dragos Roua

Can AI Improve Itself Without Training? Well, Maybe…

In

Open Intelligence

by

Dr. Fadi Shaar

nanochat: The Complete LLM Training Pipeline in One Codebase

Wali Haider

I Spent 10 Hours Training My Own Language Model Introducing Vectora v1.2

Anandha L Ranganathan

Gradient descent -Part1

In

Level Up Coding

by

Khalid Salman

I built my own dual RTX 5090 AI workstation, and here’s what renting GPUs never taught me

See more stories

Who to follow

Popular this week

QuarkAndCode

Supervised Fine-Tuning (SFT) for LLMs: Complete Guide

In

Level Up Coding

by

Khalid Salman

I built my own dual RTX 5090 AI workstation, and here’s what renting GPUs never taught me

Alex Chen

Using MinHash LSH to Find Near-Duplicate Training Data

In

Teradata Labs

by

Brandon Mincey

AI Training Checkpoint Storage: Why 128,000-GPU Clusters Break the Storage Stack

Nachiket Mehendale

Chinchilla Proved Bigger AI Models Were a Mistake

Latest stories

Dragos Roua

Can AI Improve Itself Without Training? Well, Maybe…

In

Open Intelligence

by

Dr. Fadi Shaar

nanochat: The Complete LLM Training Pipeline in One Codebase

Wali Haider

I Spent 10 Hours Training My Own Language Model Introducing Vectora v1.2

Anandha L Ranganathan

Gradient descent -Part1

In

Level Up Coding

by

Khalid Salman

I built my own dual RTX 5090 AI workstation, and here’s what renting GPUs never taught me

See more stories

Who to follow