GLiClass-Instruct Collection Multi-task efficient zero-shot sequence classification models • 3 items • Updated Apr 30 • 6
ModernBERT-TR Collection A 150M-parameter Turkish encoder family of base and downstream task models. • 20 items • Updated 6 days ago • 10
Phi-4 Collection Phi-4 family of small language, multi-modal and reasoning models. • 17 items • Updated Jul 10, 2025 • 215
view article Article NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval nvidia • 10 days ago • 57
view article Article Native-speed vLLM transformers modeling backend hmellor, lysandre • 19 days ago • 59
GLiCLass-V3 Collection Models for zero-shot text classification that are up to 50 times faster than Cross-Encoders and show the same or higher accuracy. • 8 items • Updated Jan 29 • 22
view article Article From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels drbh, danieldk • Aug 18, 2025 • 109
view article Article Profiling in PyTorch (Part 3): Attention is all you profile +2 ariG23498, sergiopaniego, sayakpaul, ror • 17 days ago • 39
view article Article SetFit: Efficient Few-Shot Learning Without Prompts +4 Unso, lewtun, luketheduke, danielkorat, orenpereg, moshew • Sep 26, 2022 • 42
From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors Paper • 2602.21778 • Published Feb 25 • 16
Off Topic Guardrail 🛡️ Collection Fast, lightweight zero-shot classifiers for user prompt's relevance to the system prompt. • 5 items • Updated Jul 28, 2025 • 5
HaloGuard 1.0 Collection Open constitutional input-prompt guards on Qwen3.5 — multilingual safe/unsafe + category classification • 2 items • Updated 24 days ago • 1