floridianfisher
Joined 13 years ago
Karma
97
Submissions
45
Member since
Apr 18
Just a dude who likes to code and stuff
View on Hacker NewsRecent submissions
Comment · 1 year ago
The purpose is research
Comment · 1 year ago
Benchmarks are on the model card https://huggingface.co/google/gemma-3-270m-it
Comment · 1 year ago
According go the Gemma 3n preview blog, Gemma 3n shares the same architecture as the upcoming version of Gemini Nano.
The ‘n’ presumably stands for Nano.
Nano is a proprietary model that ships with Android. Gemma is an open model that can be adapted and used anywhere.
Sources: https://developers.googleblog.com/en/introducing-gemma-3n/
Video in the in the blog linked in this post
Comment · 1 year ago
Try one of the smaller versions. 27b is too big for your gpu
Comment · 1 year ago
The application of modern LLM technology to animal communication is exciting.
Comment · 2 years ago
Why not try it here and make your comparisons that way? https://aistudio.google.com/app/prompts/new_chat?model=gemma...
Comment · 2 years ago
The huggingface weights are here: https://huggingface.co/collections/google/gemma-2-release-66...