SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published Feb 20, 2025 • 170
Granite 4.2 Language Models Collection Efficient reasoning and thinking language models for multilingual generation, coding, and AI assistant workflows. • 27 items • Updated 27 days ago • 55
view article Article ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third lightonai • Oct 12 • 21
view article Article Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original MultiverseComputingCAI • Aug 25 • 75
view article Article Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers tomaarsen • Aug 26 • 146
view article Article Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI nico-martin, Xenova • Sep 1 • 99
view article Article Training a coding model to paint watercolours with TRL and OpenEnv sergiopaniego • Sep 3 • 83
view article Article Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps +1 iamleonie, burtenshaw, sergiopaniego • Sep 3 • 163
view article Article NeoMME: an efficient Multimodal-native and Multilingual Encoder Hcompany • Sep 3 • 122
view article Article tokenizers v1: encode, decode and scaling, measured +2 ArthurZ, sbrandeis, mcpotato, lysandre • Sep 21 • 97
view article Article Transformers now runs llama.cpp quants +1 marcsun13, ArthurZ, lysandre • Sep 22 • 122