olmOCR Collection olmOCR is a document recognition pipeline for efficiently converting documents into plain text. olmocr.allenai.org • 4 items • Updated 4 days ago • 115
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model Paper • 2502.02737 • Published Feb 4 • 234
GraphRAG Papers Collection Research relating graphs and GenAI. For discussion, find dedicated threads on https://discord.gg/graphrag • 49 items • Updated about 18 hours ago • 35