view article Article Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps +1 iamleonie, burtenshaw, sergiopaniego • 3 days ago • 56
view article Article LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge LiquidAI • 25 days ago • 50
view article Article mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models lightonai • Jul 30 • 37
💧 LFM2.5 Collection Collection of post-trained and base LFM2.5 models. • 16 items • Updated Aug 4 • 219
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 330
MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval Paper • 2604.18584 • Published Apr 20 • 17
Luth: Efficient French Specialization for Small Language Models and Cross-Lingual Transfer Paper • 2510.05846 • Published Oct 7, 2025 • 3
🎯 Liquid Nanos Collection Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices • 36 items • Updated Aug 3 • 136
Merging in a Bottle: Differentiable Adaptive Merging (DAM) and the Path from Averaging to Automation Paper • 2410.08371 • Published Oct 10, 2024 • 3
view article Article Luth: Efficient French Specialization for Small Language Models MaxLSB • Aug 11, 2025 • 21
Cosmos-Preidct1 Collection ⚠️ This collection is archived. 👉 https://huggingface.co/collections/nvidia/cosmos3 • 14 items • Updated 26 days ago • 303
🧠 SmolLM3 Collection Smol, multilingual, long-context reasoner • 14 items • Updated Oct 9, 2025 • 109