Meet LeoLM: The First Open and Commercially Available German Foundation Language Model
Built on Llama-2 and Trained on a Massive German Text Corpus
Introducing LeoLM, the State-of-the-Art Language Model for German
LAION has released LeoLM, the first open and commercially available German foundation language model built on Llama-2. LeoLM extends Llama-2's capabilities into German through a large-scale high-quality German text corpus.
LeoLM is available in three sizes: 7B, 13B, and 70B. The 70B version, LeoLM-70B, is the largest German foundation language model to date.
LeoLM has been trained on a massive dataset of German text, including books, news articles, websites, and social media posts. This data has been carefully curated to ensure that the model is trained on high-quality content.
LeoLM can be used for a variety of natural language processing tasks, such as:
- Text classification
- Question answering
- Machine translation
- Text summarization
- Dialogue generation
LeoLM is a powerful tool that can be used to improve the performance of a wide range of applications. It is open and commercially available, making it accessible to researchers, developers, and businesses alike.
To learn more about LeoLM, visit the LAION website.
Comments