Running Featured 560 Vision Arena (Testing VLMs side-by-side) 🖼 560 Analyze images with multiple vision models for labels and boxes
llava-hf/llava-onevision-qwen2-72b-ov-hf Image-Text-to-Text • 73B • Updated Jun 18, 2025 • 1.15k • 10
view article Article Introducing Idefics2: A Powerful 8B Vision-Language Model for the community +1 Apr 15, 2024 • 191
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct Paper • 2308.09583 • Published Aug 18, 2023 • 7