The new 2B model learns from larger models through distillation and produces outsized results, DeepMind says.
The company also claims that it outperforms all GPT-3.5 models on theLMSYS Chatbot Arena leaderboard.
It’s free, every week, in your inbox.
In addition, its small enough to run on the free tier of the NVIDIA T4 deep learning accelerator.
It comes in various sizes and targets hate speech, harassment, sexually explicit content, and dangerous content.
GemmaScope focuses on transparency.
The tool comprises a collection ofsparse autoencoders(SAEs).
There are over 400 freely available SAEs covering all layers of Gemma 2 2B and 9B.
The aim is to enable researchers to create more transparent and reliable AI systems.
ShieldGemma and Gemma Scope are availablehereandhere.
Story byIoanna Lykiardopoulou
Ioanna is a writer at TNW.
With a background in the humanities, she has a soft spot for social impact-enabling technologies.
