-
Scaling test-time compute
📈587Implement test-time compute scaling for math problems
-
FineWeb: decanting the web for the finest text data at scale
🍷1.2kGenerate high-quality text data for LLMs using FineWeb
-
The Ultra-Scale Playbook
🌌3.55kThe ultimate guide to training LLM on large GPU Clusters
-
FineVision: Open Data is All You Need
📝210A new open-source dataset for training VLMs
ldwang
ldwang
AI & ML interests
LLM, MLLM, Infra
Recent Activity
Organizations
-
Scaling test-time compute
📈587Implement test-time compute scaling for math problems
-
FineWeb: decanting the web for the finest text data at scale
🍷1.2kGenerate high-quality text data for LLMs using FineWeb
-
The Ultra-Scale Playbook
🌌3.55kThe ultimate guide to training LLM on large GPU Clusters
-
FineVision: Open Data is All You Need
📝210A new open-source dataset for training VLMs
