H2O AI releases Danube, a super-tiny LLM for mobile applications
In the Hellaswag LLM benchmark evaluating common sense natural language inference, Danube performed with an accuracy of 69.58%, sitting just ...
Read moreDetailsIn the Hellaswag LLM benchmark evaluating common sense natural language inference, Danube performed with an accuracy of 69.58%, sitting just ...
Read moreDetails© 2023 earth-news.info
© 2023 earth-news.info