Giters

oeg-upm / inesdata-ml-schema

A repository to keep the vocabulary for datasets and models developed in Inesdata project

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Adding the process capacity for the model

OEG-Clark opened this issue · comments

commented

I think it will be beneficial for the users to have the max process capacity for the model in the model card. I found it very helpful from time to time when I start to use a model.

And the reason I call it max process capacity is that for NL area, it could be the max process token length. For example, ChatGPT is 2048, Llama2 is 4096. For the CV area, Vit(Visual Transformer), I believe it is 224bit $\times$ 224bit, MidJourney is 1024 $\times$ 1024 as default.

And this property is referring to the input of the model, which is vastly helpful from time to time. :)