-
Scaling test-time compute
📈593Run advanced search strategies to boost LLM problem solving
-
FineWeb: decanting the web for the finest text data at scale
🍷1.31kRead a detailed overview of the FineWeb web‑scale text dataset
-
The Ultra-Scale Playbook
🌌3.74kThe ultimate guide to training LLM on large GPU Clusters
-
FineVision: Open Data is All You Need
📝220A new open-source dataset for training VLMs
ldwang
ldwang
AI & ML interests
LLM, MLLM, Infra
Recent Activity
liked a model about 9 hours ago
deepseek-ai/DeepSeek-V3.2 liked a dataset 1 day ago
nvidia/OpenCodeInstruct liked a dataset 2 days ago
codeparrot/github-code-cleanOrganizations
-
Scaling test-time compute
📈593Run advanced search strategies to boost LLM problem solving
-
FineWeb: decanting the web for the finest text data at scale
🍷1.31kRead a detailed overview of the FineWeb web‑scale text dataset
-
The Ultra-Scale Playbook
🌌3.74kThe ultimate guide to training LLM on large GPU Clusters
-
FineVision: Open Data is All You Need
📝220A new open-source dataset for training VLMs
Misc tools for llm & vlm.