llmodel: change tokenToString to not use string_view (#968)

fixes a definite use-after-free and likely avoids some other
potential ones - std::string will convert to a std::string_view
automatically but as soon as the std::string in question goes out of
scope it is already freed and the string_view is pointing at freed
memory - this is *mostly* fine if its returning a reference to the
tokenizer's internal vocab table but it's, imo, too easy to return a
reference to a dynamically constructed string with this as replit is
doing (and unfortunately needs to do to convert the internal whitespace
replacement symbol back to a space)

gpt4all-backend/gptj.cpp

@@ -907,7 +907,7 @@ LLModel::Token GPTJ::sampleToken(PromptContext &promptCtx) const
         d_ptr->rng);
 }
 
-std::string_view GPTJ::tokenToString(Token id) const
+std::string GPTJ::tokenToString(Token id) const
 {
     return d_ptr->vocab.id_to_token[id];
 }