The Ultra-Scale Playbook
π
3.7k
The ultimate guide to training LLM on large GPU Clusters
π Research & Long-Form Blog Posts
In-depth technical articles and research pieces published by Hugging Face
-
-
The Smol Training Playbook
π3.01kThe secrets to building world-class LLMs
-
Evaluation Guidebook
π275Explore LLM benchmark trends over time
-
FineVision: Open Data is All You Need
π218A new open-source dataset for training VLMs
-
Maintain the unmaintainable
π77Explore the complex relationships between 400+ machine learning models
-
FineWeb: decanting the web for the finest text data at scale
π·1.3kGenerate a curated webβtext dataset for LLM training
-
The Eiffel Tower Llama
π108Explore the Eiffel Tower Llama experiment with open-source models
-
Porting nanochat to Transformers: an AI modeling history lesson
π45Learn about ML and Transformers through nanochat
-
FinePDFs: Liberating 3T of the finest tokens from PDFs
π66 -
Can LLMs Play the Game of Science?
π16Explore LLM science benchmark scores
-
QED-Nano: Teaching a Tiny Model to Prove Hard Theorems
π44Who needs 1T parameters? Olympiad proofs with a 4B model