Zero-To-CAD Collection Datasets (1M & 100K) and model for synthesizing executable CAD programs from an LLM in a CadQuery environment. No real data used. • 3 items • Updated 10 days ago • 11
view article Article Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents 8 days ago • 44
view article Article DeepSeek-V4: a million-token context that agents can actually use 12 days ago • 42
MediaTech Collection Collection of public datasets from the French administration, chunked, vectorized and ready to use in AI projects. • 9 items • Updated Feb 4 • 8
The ATOM Report: Measuring the Open Language Model Ecosystem Paper • 2604.07190 • Published 28 days ago • 5
Gemma-4-text-only Collection Text-only versions of gemma-4 without the vision encoders for a smaller memory and storage footprint. • 2 items • Updated 28 days ago • 7
Gemma 4 Collection Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 28 items • Updated 14 days ago • 172
PP-OCRv5 Collection PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese • 13 items • Updated Sep 15, 2025 • 56
ndl-core-collection Collection A collection of UK government structured datasets and textual sources for research, analysis, and AI applications. • 6 items • Updated Jan 12 • 3