jina-embeddings-v5-omni Collection Multimodal (text + image + video + audio) embedding models aligned with jina-embeddings-v5-text-*. Two sizes, four task variants each. • 27 items • Updated 9 days ago • 36
Running on CPU Upgrade Featured 383 ML Intern 🤖 383 Run an interactive ML assistant directly in your browser
PhysicsNeMo Collection Framework of PyTorch composable modules for developing physics guided machine learning training pipelines. https://github.com/NVIDIA/physicsnemo • 14 items • Updated 2 days ago • 17
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift • Apr 2 • 897
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published Mar 27 • 364
Running Agents Featured 209 Voxtral TTS Demo ⚡ 209 Generate realistic speech from text with custom or preset voices