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/llmodel_shared.cpp

@@ -121,7 +121,7 @@ void LLModel::prompt(const std::string &prompt,
             if (id == token) return;
         }
 
-        const std::string_view str = tokenToString(id);
+        const std::string str = tokenToString(id);
 
         // Check if the provided str is part of our reverse prompts
         bool foundPartialReversePrompt = false;