Unable to load model : We couldn't connect to 'https://huggingface.co' to load this file

[gregbugaj]

We get following error at certain times about not being able to load model from HugginFaces.
This could be due to rate limiting or service not being available.

Real cause :

   requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url:                                                                                                  
   https://huggingface.co/jinaai/jina-bert-implementation/resolve/main/configuration_bert.py 

ERROR  extract_t/rep-2@37 OSError("We couldn't connect to 'https://huggingface.co' to load this file, couldn't find it in the cached files and it looks like                        
       jinaai/jina-bert-implementation is not the path to a directory containing a file named configuration_bert.py.\nCheckout your internet connection or see                      
       how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'.") during 'WorkerRuntime' initialization                      
        add "--quiet-error" to suppress the exception details    

We should follow the instruction and implement offline-mode to allow for faster bootstrapping of the application.