Sources for what? The pareto frontier of LLMs? How Google is pretty much on the line with most of their LLM products? Or this particular model? For the first two you need to look for size/cost vs. accuracy charts. There are tons of them floating around. For the latter there is not much official info except what you can infer by analyzing the weights.bin file that Chrome downloads. But it does mention Gemini in there, so it seems pretty obvious that it is from their proprietary line of models.
All Gemini models sit around the frontier, especially if you go to smaller sizes. Google is actually more invested into efficiency than size unlike some of the other big providers.
Sources for your claim that the model being downloaded to Android/Chrome is Gemini instead of Gemma. Other than downloading the bin file myself and analyzing it lol.
Sources for what? The pareto frontier of LLMs? How Google is pretty much on the line with most of their LLM products? Or this particular model? For the first two you need to look for size/cost vs. accuracy charts. There are tons of them floating around. For the latter there is not much official info except what you can infer by analyzing the weights.bin file that Chrome downloads. But it does mention Gemini in there, so it seems pretty obvious that it is from their proprietary line of models.
Just because it's called Gemini doesn't mean that it's somehow automatically as comparable with the frontier of small models as well, does it?
All Gemini models sit around the frontier, especially if you go to smaller sizes. Google is actually more invested into efficiency than size unlike some of the other big providers.
1 reply →
Sources for your claim that the model being downloaded to Android/Chrome is Gemini instead of Gemma. Other than downloading the bin file myself and analyzing it lol.
How about Google itself?
https://developer.chrome.com/docs/ai/prompt-api
>With the Prompt API, you can send natural language requests to Gemini Nano in the browser.
4 replies →