[SOLVED]RASA NLU misbehaving when trained on server but works when trained on local

So it’s solved . As i was using SVM , i just kept the following modules similar and now the issue is solved.

  • Spacy and Spacy Model (be careful to use similar model i.e sm or md or lg) [Be very specific about it ]
  • sklearn
  • scipy
  • sklearn-crf suite
  • Numpy

Make sure you agree on to py3 or py2 . Minor version mismatch wont impact.