If train the GPT-2 [architecture] from scratch on enwik9 for your benchmark 
Matt, don't we throw away the model once done the file? There is no problem 
with size then during training. So why isn't GPT-2 put against your contenst?
------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/Tcc6753a33ad48f78-Me2a89c94513fc84cc8017412
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to