Scaling test-time compute
📈
592
Run advanced LLM search strategies to boost problem solving
MiscSpaces
-
-
FineWeb: decanting the web for the finest text data at scale
🍷1.29kRead about FineWeb, a large web‑text dataset for LLMs
-
The Ultra-Scale Playbook
🌌3.68kThe ultimate guide to training LLM on large GPU Clusters
-
FineVision: Open Data is All You Need
📝218A new open-source dataset for training VLMs
-
Megatron Memory Estimator
👁19Estimate GPU memory usage for Megatron models
-
Smol2Operator Demo
🐢19Smol2Operator Demo: GUI Agent Model
-
The Smol Training Playbook
📚2.98kThe secrets to building world-class LLMs
-
Unlocking On-Policy Distillation for Any Model Family
📝84Explore on‑policy distillation with interactive visualizations