ViDoRe Benchmark Collection Benchmark for document retrieval using visual features, introduced in the ColPali paper. Datasets are using the QA format. • 10 items • Updated Jan 23, 2025 • 20
ViDoRe Benchmark V3 Collection ViDoRe V3 is our latest benchmark, engineered to set a new industry gold standard for multi-modal, enterprise document retrieval evaluation. • 8 items • Updated Nov 5, 2025 • 16
Running 3.62k The Ultra-Scale Playbook 🌌 3.62k The ultimate guide to training LLM on large GPU Clusters
SauerkrautLM-Multilingual-(Reason)-ColBERT Collection SauerkrautLM ColBERT is a suite of Late-Interaction retrieval models built with PyLate’s ColBERT architecture and tuned for seven European languages. • 7 items • Updated Aug 3, 2025 • 20
view article Article DualPipe Explained: A Comprehensive Guide to DualPipe That Anyone Can Understand—Even Without a Distributed Training Background Feb 28, 2025 • 14
view article Article Training and Finetuning Embedding Models with Sentence Transformers v3 May 28, 2024 • 262
sentence-transformers/all-MiniLM-L6-v2 Sentence Similarity • 22.7M • Updated Mar 6, 2025 • 144M • • 4.29k