Scaling test-time compute
📈
602
Explore test-time compute scaling methods for LLMs
MiscSpaces
-
-
FineWeb: decanting the web for the finest text data at scale
🍷1.46kExplore the FineWeb dataset and its creation process
-
The Ultra-Scale Playbook
🌌4.09kThe ultimate guide to training LLM on large GPU Clusters
-
FineVision: Open Data is All You Need
📝236A new open-source dataset for training VLMs
-
Megatron Memory Estimator
👁19Estimate GPU memory usage for Megatron models
-
Smol2Operator Demo
🐢20Smol2Operator Demo: GUI Agent Model
-
The Smol Training Playbook
📚3.34kThe secrets to building world-class LLMs
-
Unlocking On-Policy Distillation for Any Model Family
📝122Explore on‑policy distillation visualizations for any model