Scaling test-time compute
📈
596
Run advanced search strategies to boost LLM problem solving
Built with Distill blog ❤️
Collection of all interactive blogs built on top of Distill template. To create your own check: https://huggingface.co/spaces/lvwerra/distill-blog-tem
-
-
Open-LLM performances are plateauing, let’s make the leaderboard steep again
🏔127Explore and compare advanced language models on a new leaderboard
-
Scaling FineWeb to 1000+ languages: Step 1: finding signal in 100s of evaluation tasks
📝91Evaluate multilingual models using FineTasks
-
The Ultra-Scale Playbook
🌌3.8kThe ultimate guide to training LLM on large GPU Clusters
-
FineWeb: decanting the web for the finest text data at scale
🍷1.33kExplore and download the FineWeb web‑text dataset
-
The Distill Template
🌌46Craft Beautiful Blogs