Tag

#gemma

Every item tagged gemma, newest first.

2 items

DiffusionGemma

Google's experimental Gemini Diffusion model has re-emerged as an open-weight Gemma model called DiffusionGemma. The 26B parameter model is licensed under Apache 2 and is available on NVIDIA's NIM cloud API. It runs at 857 tokens/second. You can use it for free via the NIM API.

Key takeaways

DiffusionGemma is an open-weight, Apache 2 licensed model.
Runs at 857 tokens/second.
Available for free on NVIDIA's NIM cloud API.

SSimon Willison#open-weights #gemma #diffusion-models

modelsJun 27

Welcome Gemma 2 - Google’s new open LLM

Google released Gemma 2, a new open LLM available on Hugging Face. Gemma 2 builds on the first Gemma model, with performance and efficiency improvements. You can access Gemma 2 through Hugging Face’s model hub. The release expands Google’s open model offerings.

Key takeaways

Gemma 2 is available on Hugging Face.
Performance and efficiency improvements over Gemma 1.
Part of Google’s expanded open model offerings.

HHugging Face Blog#open-llm #hugging-face #gemma