PaliGemma
An open-source vision-language model released by Google that supports simultaneous processing of image and text inputs. Model weights are freely downloadable and the model can be deployed locally or on private servers without relying on Google's cloud API.
Timeline (last 90 days)
PaliGemma is an open-source vision-language model from Google; its weights can be downloaded for free and run locally or on a private server without relying on Google's cloud API.
Google's specialized Gemma models include: EmbeddingGemma for text embedding and semantic search, FunctionGemma for tool calling, PaliGemma focused on vision, and ShieldGemma focused on safety
PaliGemma uses SigLIP as the vision encoder and is a combined architecture of a vision encoder and a language model.
All Facts (3)
PaliGemma is an open-source vision-language model from Google; its weights can be downloaded for free and run locally or on a private server without relying on Google's cloud API.
50%UnverifiedGoogle's specialized Gemma models include: EmbeddingGemma for text embedding and semantic search, FunctionGemma for tool calling, PaliGemma focused on vision, and ShieldGemma focused on safety
50%UnverifiedPaliGemma uses SigLIP as the vision encoder and is a combined architecture of a vision encoder and a language model.
50%