https://developers.googleblog.com/en/introducing-paligemma-2-powerful-vision-language-models-simple-fine-tuning/ Google for Developers Products * Develop * Android * Chrome * ChromeOS * Cloud * Firebase * Flutter * Google Assistant * Google Maps Platform * Google Workspace * TensorFlow * YouTube * Grow * Firebase * Google Ads * Google Analytics * Google Play * Search * Web Push and Notification APIs * Earn * AdMob * Google Ads API * Google Pay * Google Play Billing * Interactive Media Ads Solutions Events Learn Community * Groups * Google Developer Groups * Google Developer Student Clubs * Woman Techmakers * Google Developer Experts * Tech Equity Collective * Programs * Accelerator * Solution Challenge * DevFest * Stories * All Stories Developer Program Blog [ ] Search English * English * Espanol (Latam) * Bahasa Indonesia * Ri Ben Yu * hangugeo * Portugues (Brasil) * Jian Ti Zhong Wen Google for Developers * Products + More * Solutions * Events * Learn * Community + More * Developer Program * Blog * Develop * Android * Chrome * ChromeOS * Cloud * Firebase * Flutter * Google Assistant * Google Maps Platform * Google Workspace * TensorFlow * YouTube * Grow * Firebase * Google Ads * Google Analytics * Google Play * Search * Web Push and Notification APIs * Earn * AdMob * Google Ads API * Google Pay * Google Play Billing * Interactive Media Ads * Groups * Google Developer Groups * Google Developer Student Clubs * Woman Techmakers * Google Developer Experts * Tech Equity Collective * Programs * Accelerator * Solution Challenge * DevFest * Stories * All Stories [English ] Gemma Introducing PaliGemma 2: Powerful Vision-Language Models, Simple Fine-Tuning DEC 05, 2024 Daniel Keysers Research Engineer Andreas Steiner Staff Software Engineer Share * Facebook * Twitter * LinkedIn * Mail * PaliGemma2_BlogHeader Building custom, advanced AI that can "see" used to be a complex and resource-intensive endeavor. Not anymore. This past May, we launched PaliGemma, the first vision-language model in the Gemma family, taking a significant step toward making class-leading visual AI more accessible. Now, we're thrilled to introduce PaliGemma 2, the next evolution in tunable vision-language models. PaliGemma 2 builds upon the performant Gemma 2 models, adding the power of vision and making it easier than ever to fine-tune for exceptional performance. With PaliGemma 2, these models can see, understand, and interact with visual input, opening up a world of new possibilities. What's new in PaliGemma 2? * Scalable performance: Optimize performance for any task with PaliGemma 2's multiple model sizes (3B, 10B, 28B parameters) and resolutions (224px, 448px, 896px). * Long captioning: PaliGemma 2 generates detailed, contextually relevant captions for images, going beyond simple object identification to describe actions, emotions, and the overall narrative of the scene. * Expanding to new horizons: Our research demonstrates leading performance on chemical formula recognition, music score recognition, spatial reasoning, and chest X-ray report generation, as detailed in the technical report. Upgrading to PaliGemma 2 is a breeze for existing PaliGemma users. It's designed as a drop-in replacement, offering a range of model sizes with immediate performance gains on most tasks without major code modifications. Additionally, its flexibility makes fine-tuning for specific tasks and datasets straightforward, empowering you to tailor its capabilities to your precise needs. You can learn more about how PaliGemma 2 works, including when to use more parameters and larger resolutions, in our technical report. Building on the success of PaliGemma Since its launch, the Gemma family has rapidly grown into a vibrant ecosystem--the Gemmaverse--with tens of thousands of models and applications. This rapid growth is a testament to the community's ingenuity. Early innovations using PaliGemma, such as ColPali's advancements in visual document retrieval, RoboFlow's fine-tuning techniques, and progress in real-time object tracking, demonstrate the expanding potential of the Gemmaverse. Get started today Ready to explore the potential of PaliGemma 2? Here's how: * Download models & code: Find the pre-trained models and code on Hugging Face and Kaggle. * Learn & integrate: Dive into our comprehensive documentation and example notebooks to quickly integrate these powerful tools into your projects. For PaliGemma, start with our inference notebook then try fine-tuning with a custom dataset. * Use your preferred framework: Leverage your preferred tools and frameworks, including Hugging Face Transformers, Keras, PyTorch, JAX, and Gemma.cpp. We're incredibly excited to see what you create with PaliGemma 2. Join the vibrant Gemma community, share your projects to the Gemmaverse, and let's continue to explore the boundless potential of AI together. Your feedback and contributions are invaluable in shaping the future of these models and driving innovation in the field. posted in: * Gemma * AI * Announcements * Explore * Multimodal AI models Previous Next Related Posts 7 examples of Gemini's multimodal capabilities in action Gemini AI Announcements Industry Trends 7 examples of Gemini's multimodal capabilities in action Nov. 25, 2024 Inference with Gemma using Dataflow and vLLM Gemma AI Cloud How-To Guides Problem-Solving Inference with Gemma using Dataflow and vLLM Nov. 13, 2024 Introducing Google Developer Program premium membership Cloud Announcements Community Introducing Google Developer Program premium membership Nov. 25, 2024 Introducing Keras Hub: Your one-stop shop for pretrained models Gemma AI Announcements Best Practices Introducing Keras Hub: Your one-stop shop for pretrained models Oct. 22, 2024 Join us at the Women in AI Summit 2024! AI Community Events Join us at the Women in AI Summit 2024! Nov. 22, 2024 * Connect + Blog + Instagram + LinkedIn + Twitter + YouTube * Programs + Women Techmakers + Google Developer Groups + Google Developer Experts + Accelerators + Google Developer Student Clubs * Developer consoles + Google API Console + Google Cloud Platform Console + Google Play Console + Firebase Console + Actions on Google Console + Cast SDK Developer Console + Chrome Web Store Dashboard Google for Developers * Android * Chrome * Firebase * Google Cloud Platform * All products * Manage cookies * Terms * Privacy English * English * Espanol (Latam) * Bahasa Indonesia * Ri Ben Yu * hangugeo * Portugues (Brasil) * Jian Ti Zhong Wen