|We are excited to announce Cedille, the largest language model for French (6b parameters).|
Language models are general purpose AI systems that are able to solve a range of tasks by simply being prompted for it. It can be used for example to summarize text, do translations, or for idea generation & overcoming writer's block.
You may know GPT-3, the humongous model from OpenAI. Cedille is a similar model targeting the French demographic - but smaller, as we don’t yet have $1b in the bank like they do. Although GPT-3 supports multiple languages including French, our model is competitive with GPT-3 on a range of French tasks! Plus, of course we’re open source while they keep their model closed and heavily restrict access to it.
You can try it out right away from our playground: https://app.cedille.ai
We are proponents of “open AI” and as such have released a checkpoint for the world to use (MIT license): https://github.com/coteries/cedille-ai
One of the problems with large language models is the potentially toxic, sexist or in other ways unpleasant output. We tried our best to avoid this issue by doing extensive dataset filtering. As a result, our benchmark indicates that Cedille is indeed less toxic than GPT-3.