NS mode as default

Experimental change that makes NS the default, more and more models seem to be requiring this as megatron based models are getting traction, neither does this seem to break the original models (with the exception of a user not being able to use </s> in generated outputs, the extremely rare case someone would be effected by this they can manually switch the mode by editing their settings file).

If this breaks nothing ns will remain the default, however the n mode should remain a choice for those who need it. In case it does get reversed I have also added the bloom model type to the ns list since its models require this.

aiserver.py

@@ -339,7 +339,7 @@ class vars:
     rngpersist  = False
     nogenmod    = False
     welcome     = False  # Custom Welcome Text (False is default)
-    newlinemode = "n"
+    newlinemode = "ns"
     quiet       = False # If set will suppress any story text from being printed to the console (will only be seen on the client web page)
     debug       = False # If set to true, will send debug information to the client for display
     lazy_load   = True  # Whether or not to use torch_lazy_loader.py for transformers models in order to reduce CPU memory usage
@@ -661,7 +661,7 @@ def loadmodelsettings():
             js   = {}
     if vars.model_type == "xglm" or js.get("compat", "j") == "fairseq_lm":
         vars.newlinemode = "s"  # Default to </s> newline mode if using XGLM
-    if vars.model_type == "opt":
+    if vars.model_type == "opt" or vars.model_type == "bloom":
         vars.newlinemode = "ns"  # Handle </s> but don't convert newlines if using Fairseq models that have newlines trained in them
     vars.modelconfig = js
     if("badwordsids" in js):