TIPSv2 Collection TIPSv2 foundational vision-language models. Webpage: https://gdm-tipsv2.github.io/ • 9 items • Updated Apr 14 • 32
google/gemma-4-26B-A4B-it Image-Text-to-Text • 27B • Updated about 12 hours ago • 10.5M • • 1.01k
Running on CPU Upgrade Agents 245 MMLU-Pro Leaderboard 🥇 245 More advanced and challenging multi-task evaluation
google/embeddinggemma-300m Sentence Similarity • 0.3B • Updated Sep 25, 2025 • 1.96M • • 1.67k
fancyfeast/llama-joycaption-beta-one-hf-llava Image-Text-to-Text • 8B • Updated May 16, 2025 • 119k • 350
laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K Zero-Shot Image Classification • Updated May 16, 2023 • 58.1k • 124