PaliGemma2-3b-pt-448 is a 3-billion parameter vision-language model developed by Google. It accepts image and text inputs and generates text outputs, supporting tasks such as visual question answering, captioning, and multimodal reasoning. The model is distributed as open weights on Hugging Face, compatible with the Transformers library, and can be run locally or via cloud inference providers.
Paligemma2 3b Pt 448 is a Foundation models & chat product. It focuses on running state-of-the-art multimodal vision-language inference without building models from scratch. It is built as an open-source project for developers. Paligemma2 3b Pt 448 is open source under the Open Source license. The product ships for the web, the command line, and API.
Google builds and maintains Paligemma2 3b Pt 448, and the product first shipped in 2024. Key capabilities include vision-language model, image-text-to-text, and transformers compatible.
Latest indexed changes and source events
google/paligemma2-3b-pt-448 verified by the PulseGate indexer
Other apps tracked under the same category.
