E-MM1 Collection Multimodal embedding model, supporting datasets, and a paper describing the process going into building both the datasets and the models 🤗 • 6 items • Updated 8 days ago • 10
gliner2 family Collection GLiNER2 extends the original GLiNER architecture to support multi-task information extraction with a schema-driven interface. This base model provides • 3 items • Updated 23 days ago • 8
Commit Message Bot Collection Collection of models to help draft git commit messages locally • 1 item • Updated 22 days ago • 1
PII Redaction Collection We trained and released a family of small language models (SLMs) specialized for policy-aware PII redaction. • 7 items • Updated Oct 20 • 5
GLiNER-PII Collection PII detection models developed in collaboration with Wordcab • 5 items • Updated Sep 24 • 21
Apertus LLM Collection Democratizing Open and Compliant LLMs for Global Language Environments: 8B and 70B open-data open-weights models, multilingual in >1000 languages • 4 items • Updated Oct 1 • 304
VibeVoice Collection Frontier Text-to-Speech Models https://microsoft.github.io/VibeVoice/ • 7 items • Updated 10 days ago • 135
GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface Paper • 2507.18546 • Published Jul 24 • 28
view article Article Introducing AI Sheets: a tool to work with datasets using open AI models! Aug 8 • 105
view article Article Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face Jul 29 • 199
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 • 18
view article Article Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders Jul 9 • 720
💧 LFM2 Collection LFM2 is a new generation of hybrid models, designed for on-device deployment. • 22 items • Updated 24 days ago • 119
Phi-4 Collection Phi-4 family of small language, multi-modal and reasoning models. • 17 items • Updated Jul 10 • 191
SmolLM2 Collection State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated May 5 • 294
view article Article Train 400x faster Static Embedding Models with Sentence Transformers Jan 15 • 219