Mistral Medium 3.5 Collection Our first flaship models handling instruction-following, reasoning, and coding in a single set of opened-weights. • 2 items • Updated 1 day ago • 8
gpt-oss-safeguard Collection gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss • 2 items • Updated Oct 29, 2025 • 72
Gemma 4 Collection Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 28 items • Updated 9 days ago • 166
Holo2 Collection Holo2 - Cost-Efficient Models for Cross-Platform Computer-Use Agents • 4 items • Updated Feb 2 • 27
Inference Optimized Checkpoints (with Model Optimizer) Collection A collection of generative models quantized and optimized for inference with Model Optimizer. • 65 items • Updated about 6 hours ago • 150
ERDES — Ocular Ultrasound Classification All Tasks Collection ERDES benchmark: 8 architectures × 5 ocular ultrasound classification tasks. Paper: arXiv:2508.04735 | Dataset: pcvlab/erdes • 59 items • Updated Mar 5 • 1
ERDES: A Benchmark Video Dataset for Retinal Detachment and Macular Status Classification in Ocular Ultrasound Paper • 2508.04735 • Published Aug 5, 2025 • 2
Open Legal Data Collection A collection of our favorite open-source legal datasets on Hugging Face. • 15 items • Updated Mar 14 • 7
Explainable AI through a Democratic Lens: DhondtXAI for Proportional Feature Importance Using the D'Hondt Method Paper • 2411.05196 • Published Nov 7, 2024 • 1
Open-AgentRL Collection RLAnything & DemyAgent: Open-Source RL for LLMs and Agentic Scenarios • 12 items • Updated Feb 3 • 7
MiniCPM-o & MiniCPM-V Collection Multimodal models with leading performance. • 29 items • Updated 25 days ago • 78
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning Paper • 2509.24650 • Published Sep 29, 2025 • 11