Never exit the main loop in interactive mode.

If the end of stream token mark is found, when in interactive mode, ask
for user input instead of exiting the main loop.

In case of running out of token budget, reset it and ask for user input.

With these changes, embd can end up empty and cause a crash in the next
iteration of the loop, so we check for its size as well.

main.cpp

@@ -1035,10 +1035,20 @@ int main(int argc, char ** argv) {
             }
         }
 
-        // end of text token
+        if (params.interactive) {
-        if (embd.back() == 2) {
+            if (embd.size() && embd.back() == 2) {
-            fprintf(stderr, " [end of text]\n");
+                is_interacting = true;
-            break;
+            }
+            if (remaining_tokens == 0) {
+                remaining_tokens = params.n_predict;
+                is_interacting = true;
+            }
+        } else {
+            // end of text token
+            if (embd.size() && embd.back() == 2) {
+                fprintf(stderr, " [end of text]\n");
+                break;
+            }
         }
     }