AI for everyone with Gemma
summary
Gemma is a family of open models released eight months ago with 2B, 9B, and 27B parameter variants; the 27B tops LLM chatbot leaderboards against models 2–10x larger while the 2B outperforms GPT‑3.5 on LLMs. The ecosystem already has 40,000 variants on Hugging Face, plus ShieldGemma safety classifiers and Gemma Scope interpretability tools, an expansive tokenizer for hundreds of thousands of tokens, and a $100,000 Kaggle competition to tune models for new languages.
AI-written summary · about
related talks
15mGemma, DeepMind's Family of Open Models
10mDemo: Using Gemma with the Hugging Face ecosystem
44mBuilding amazing Front-End Project with Gemma: A State-of-the-Art Open Model
07mWelcome to the Gemmaverse
12mWelcome to Gemma 3
12mGemma: The responsible way to build
39mFlutter Project with Gemma: A State-of-the-Art Open Model
16mOpen models in the Gemini era