Both my benchmark and the Hutter prize include the size of the decompressor, including any training data. GPT-2 was trained on lots of data. It might work trained only on enwik9 but I don't think it was designed that way. It would be an interesting experiment.
On Mon, Jul 19, 2021, 8:23 AM <[email protected]> wrote: > No but on your contest, why couldn't he use GPT-2 as is? What changes had > to be made and why? I remember hearing GPT-2 was non-deterministic, but > what else besides that? > *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/Tcc6753a33ad48f78-M304fb4db2f01303ca712c5c0> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tcc6753a33ad48f78-M660127bb733b1240b1f8e3a0 Delivery options: https://agi.topicbox.com/groups/agi/subscription
