You will have to read the papers to see how they calculated perplexity. Let us know.
On Wed, Sep 15, 2021, 9:30 AM <[email protected]> wrote: > Are you saying all those marks on that bench linked above *are* following > the same methods so results are comparable, or that they are not so they > can publish a only slightly better score? > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + > delivery options <https://agi.topicbox.com/groups/agi/subscription> > Permalink > <https://agi.topicbox.com/groups/agi/Tc9a99c50a9ec758e-M23560b30ec1ee18525ff40d6> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tc9a99c50a9ec758e-M5d0a6b19c3efdedf3f52b115 Delivery options: https://agi.topicbox.com/groups/agi/subscription
