Comment Comment by onlyrealcuzzo Probably a better link: https://developers.googleblog.com/en/introducing-gemma-3n/Gemma 3n is a model utilizing Per-Layer Embeddings to achieve an on-device memory footprint of a 2-4B parameter model.At the same time, it performs nearly as well as Claude 3.7 Sonnet in Chatbot Arena. parent onlyrealcuzzo 1 year ago
Gemma 3n is a model utilizing Per-Layer Embeddings to achieve an on-device memory footprint of a 2-4B parameter model.
At the same time, it performs nearly as well as Claude 3.7 Sonnet in Chatbot Arena.