serve: Google Cloud - "ResourceNotFoundException"

I followed the instructions here for creating a docker repo with my model for Google Cloud deployment:

https://cloud.google.com/blog/topics/developers-practitioners/pytorch-google-cloud-how-deploy-pytorch-models-vertex-ai

When I run a health check, I get

curl localhost:7080/ping
{
  "status": "Healthy"
}

When I try:

curl -s -X POST \
  -H "Content-Type: application/json; charset=utf-8" \
  -d @./predictor/instances.json \
  http://localhost:7080/predictions/conv1dppm/

I get the error:

{
  "code": 404,
  "type": "ResourceNotFoundException",
  "message": "Requested resource is not found, please refer to API document."
}

So I should refer to the API. Except when I do that, nothing works. I have tried:

curl localhost:7080/models
curl localhost:7081/models
curl localhost:7080/models/all
curl localhost:7080/conv1dppm
etc.

Everything gives back that same error or something similar. Has anyone had any success deploying a model on Google Cloud? If not there, where? Why is the model “healthy” when it clearly doesn’t look healthy?