Gemma
model Your tags
Your notes
Google's first open-weight models, built on Gemini research. 2B and 7B dense Transformers. Outperformed similarly sized open models on 11 of 18 text-based tasks.
Gemma established Google's commitment to open-weight releases alongside its proprietary Gemini line. Apache 2.0. By the Gemma Team.
Model Details
Architecture DENSE
Parameters 7B
Variants
| Name | Parameters | Notes |
|---|---|---|
| Gemma 2B | 2B | — |
| Gemma 7B | 7B | — |