OpenGPT-X research projectLarge AI language model published
The large AI language model of the OpenGPT-X research project is now available for download on Hugging Face: "Teuken-7B" was trained from scratch with the 24 official languages of the EU and comprises 7 billion parameters.
Page [2 of 4]
 | | | Image 2 of 4 | | | |
The diagram shows the additional computing power required to process a non-English text with the tokenizer associated with the language model (in % compared to Llama 3). In comparison, Teuken models require the least amount of additional computing power and therefore incur the lowest surcharge for multlingual queries to the model. © Fraunhofer IAIS