Theseus 6/768 is an AI model developed by University of California San Diego, Beihang University and Microsoft (United States and China), first published in February 2020. It works in the language domain, on tasks such as text autocompletion.
Epoch AI has no training-compute estimate for this model. The model has 66,000,000 parameters. It was trained on roughly 393K datapoints. Training ran on NVIDIA V100.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of BERT-Large. The reference paper has 224 citations. Epoch AI rates the confidence of this record as confident.