Does Gemma 2 9B Support All Listed Languages on the Gemini 1.5 Page?

#33
by i18n-site - opened

I noticed on the Google page that Gemini supports the following languages, but the page only mentions Gemini 1.5.

I'm curious to know if Gemma 2 9B are also supports all these languages ?

https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models?hl=en#languages-gemini
Gemini models support the following languages:
Arabic (ar), Bengali (bn), Bulgarian (bg), Chinese simplified and traditional (zh), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Finnish (fi), French (fr), German (de), Greek (el), Hebrew (iw), Hindi (hi), Hungarian (hu), Indonesian (id), Italian (it), Japanese (ja), Korean (ko), Latvian (lv), Lithuanian (lt), Norwegian (no), Polish (pl), Portuguese (pt), Romanian (ro), Russian (ru), Serbian (sr), Slovak (sk), Slovenian (sl), Spanish (es), Swahili (sw), Swedish (sv), Thai (th), Turkish (tr), Ukrainian (uk), Vietnamese (vi).

Hi @i18n-site , The Gemma 2 9B model is trained on a vast dataset of text and code, enabling support for a diverse range of languages.

To determine the language support of the Gemma 2 9B model, you can analyze its vocabulary by searching for specific language alphabets or tokens. For example, to verify if the model supports Telugu, you can check if a particular Telugu character is present in the vocabulary. If it is found, you can conclude that the model supports the Telugu language. Similarly, you can perform this check for other languages by searching for their respective characters or tokens in the model's vocabulary. Kindly find the below screenshot. Thank you.

image.png

Sign up or log in to comment