Don't force immediate interactive without -i

Sometimes we might want to use a reverse prompt but we want to let
the model generate tokens right after the initial prompt. So we don't
force user input mode if the `-i` flag wasn't specified and instead
let it run until we encounter the reverse prompt.

Author: Johnman

main.cpp

@@ -885,6 +885,8 @@ int main(int argc, char ** argv) {
         antipromptv_inp.push_back(::llama_tokenize(vocab, antiprompt, false));
     }
 
+    const bool initially_interacting = params.interactive;
+
     // enable interactive mode if reverse prompt is specified
     if (antipromptv_inp.size() != 0) {
         params.interactive = true;
@@ -942,7 +944,7 @@ int main(int argc, char ** argv) {
 #endif
                " - Press Return to return control to LLaMa.\n"
                " - If you want to submit another line, end your input in '\\'.\n\n");
-        is_interacting = true;
+        is_interacting = initially_interacting;
     }
 
     int input_consumed = 0;