* Update config.py
* new option
Allow a new option from the settings : tell is a reader model can return a "no answer" like SQuAD2.0 models, or if it's only a SQuAD1.0-like model, always giving an answer.
* fix gpu CMD and set tag to latest
* udpate dockerfiles. resolve race condition of index creation with multiple workers
* update dockerfiles for preload. remove try catch for elastic index creation
* add back try/catch. disable multiproc in default config to comply with --preload of gunicorn
* change to pip3 for GPU dockerfile
* remove --preload for gpu
