Re:Octopus v2: On-device language model for super agent
by alwa on Wednesday April 03, 2024 @05:53AM
(#39915344)
Figure 2 is incredible.
With only passing familiarity with the norms in this kind of work, the accuracy rates of all models on this benchmark suite seem suspiciously (and uniformly) high. Is choosing the right intention among “20 vehicle functions” or “20 Android APIs” consistent with an ordinary level of ambition in this kind of research these days?
With only passing familiarity with the norms in this kind of work, the accuracy rates of all models on this benchmark suite seem suspiciously (and uniformly) high. Is choosing the right intention among “20 vehicle functions” or “20 Android APIs” consistent with an ordinary level of ambition in this kind of research these days?