74 results
SEPT. 5, 2024 / Gemma
PaliGemma, a lightweight open vision-language model (VLM), is able to take both image and text inputs and produce a text response, adding an additional vision model to the BaseGemma model.
AUG. 29, 2024 / Gemma
RecurrentGemma architecture showcases a hybrid model that mixes gated linear recurrences with local sliding window attention; a highly valuable feature when you're concerned about exhausting your LLM's context window.
AUG. 22, 2024 / Gemma
Gemma 2 is a new suite of open models that sets a new standard for performance and accessibility, outperforming popular models more than twice its size.
AUG. 16, 2024 / Gemma
Use the Gemma language model to gauge customer sentiment, summarize conversations, and assist with crafting responses in near real-time with minimal latency.
AUG. 15, 2024 / Gemma
Learn more about the different variations of Gemma models, how they are designed for different use cases, and the core parameters of their architecture.
AUG. 14, 2024 / Gemma
Create a text-based adventure game using Gemma 2. Here are code snippets and tips for designing the game world, enhancing interactivity and replayability, and more.
AUG. 13, 2024 / Mobile
XNNPack, the default TensorFlow Lite CPU inference engine, has been updated to improve performance and memory management, allow cross-process collaboration, and simplify the user-facing API.
JULY 31, 2024 / Gemma
ShieldGemma is a suite of safety content classifiers models built upon Gemma2 designed to keep users safe. GemmaScope is a new model interpretability tool that offers unparalleled insight into our models' inner workings.
JULY 17, 2024 / Go
Genkit for Go is an open source framework for building AI-powered applications in Go. It leverages Go's simplicity, scalability, and security, and is currently in alpha.
JULY 17, 2024 / Mobile
Google's I/O Connect event in Bengaluru highlighted India's contributions to AI and introduced new tools for app development, including AI agents for coding and testing.
