exantech
diff --git a/‎llama_cpp/llama.py
Copy file name to clipboardExpand all lines: llama_cpp/llama.py
+1-1Lines changed: 1 addition & 1 deletion b/‎llama_cpp/llama.py
Copy file name to clipboardExpand all lines: llama_cpp/llama.py
+1-1Lines changed: 1 addition & 1 deletion
@@ -953,7 +953,7 @@ def _create_completion(
                     token_end_position += len(self.detokenize([token]))
                     # Check if stop sequence is in the token
                     if token_end_position >= (
-                        remaining_length - first_stop_position - 1
+                        remaining_length - first_stop_position
                     ):
                         break
                     logprobs_or_none: Optional[CompletionLogprobs] = None