You can look up the torchvision model zoo for pretrained weights of most popular architectures.
Tensorflow as an equivalent tool but I can't remember the name.
The models have to be trained. Trained towards a given task.
And then once you have the weights you have to figure out what to do with them. Data science (training a good model) and engineering (deploying it as a service to be consumed by end users) are pretty distinct tasks.