view article Article Ulysses Sequence Parallelism: Training with Million-Token Contexts 4 days ago • 14
view article Article 🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do 2 days ago • 35
view changelog Hugging Face Changelog Introducing Buckets: S3-like storage on the Hub 2 days ago • 102
view article Article FlashAttention, Streaming Algorithms, and Numerical Stability in Modern ML Systems 2 days ago • 1
Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored Collection Min 256k context + images : Reg, Heretic, Heretic fine tunes of Qwen 3.5 in all sizes. • 31 items • Updated about 23 hours ago • 13
Nanochat — The First Moroccan Darija Language Model Family Collection Nanochat Moroccan Model Family: models built for Moroccan Darija. Includes the Base model, the raw Instruct checkpoint, and the HF-compatible Instruct • 8 items • Updated 4 days ago • 2
view article Article Konkani LLM: Bringing a Multi-Script Low-Resource Language to the AI Era 6 days ago • 7
Meta APO Collection Model of MetaAPO https://arxiv.org/abs/2509.23371 • 6 items • Updated 13 days ago • 2
FINAL Bench Collection World's First Functional Metacognition Benchmark. "Not how much AI knows — but whether it knows what it doesn't know, and can fix it." • 2 items • Updated 20 days ago • 4
view article Article Introducing Kanon 2 Enricher — the world’s first hierarchical graphitization model 10 days ago • 6
Qwen Image Edit [Layout Bbox] Collection Collection of Region Bounding LoRAs • 7 items • Updated about 9 hours ago • 4