Mistral Small 4 Collection A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated 1 day ago • 48
Bielik-11B-v3.0 Collection A collection of models based on Bielik-11B-v3.0 - instruct and quantized versions. • 5 items • Updated Dec 31, 2025 • 7
view changelog Hugging Face Changelog Introducing Buckets: S3-like storage on the Hub 8 days ago • 169
Heterogeneous Agent Collaborative Reinforcement Learning Paper • 2603.02604 • Published 15 days ago • 180
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders Paper • 2603.06569 • Published 12 days ago • 108
Helios Collection Helios: 14B Real-Time Long Video Generation Model can be Cheaper, Faster but Keep Stronger than 1.3B ones • 7 items • Updated 3 days ago • 22
DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference Paper • 2602.21548 • Published 21 days ago • 45
Discovering Multiagent Learning Algorithms with Large Language Models Paper • 2602.16928 • Published 28 days ago • 16
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 26 days ago • 487
jina-embeddings-v5-text: Task-Targeted Embedding Distillation Paper • 2602.15547 • Published 29 days ago • 26
jina-embeddings-v5-text Collection Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification. • 29 items • Updated 19 days ago • 35
PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models Paper • 2602.06053 • Published Jan 14 • 8