FineWeb: decanting the web for the finest text data at scale
Explore and download the FineWeb webβscale text dataset
Explore the Eiffel Tower Llama experiment with open-source models
Explore LLM benchmark scores over time
Explore on-policy distillation visualization for any model
TRL distillation for 100B+ teachers, 40x faster
Explore an annotated DeepSeek-V4 paper with interactive notes
The secrets to building world-class LLMs
The ultimate guide to training LLM on large GPU Clusters
Visualize embeddings in 3D space, powered by EmbeddingGemma
Test your knowledge of the Transformers Fundementals
Explore code-generation model leaderboards and task details
Retrieve top similar articles based on topic and subtopic
Display a message about course certification relocation