diff --git a/convert-gpt4all-to-ggml.py b/convert-gpt4all-to-ggml.py
index b1a5e0560..92bcf94fd 100644
--- a/convert-gpt4all-to-ggml.py
+++ b/convert-gpt4all-to-ggml.py
@@ -10,7 +10,6 @@ import argparse
 import glob
 import os
 import struct
-import sys
 from sentencepiece import SentencePieceProcessor
 
 HPARAMS = keys = ["vocab_size", "dim", "multiple_of", "n_heads", "n_layers"]
@@ -56,7 +55,7 @@ def write_tokens(fout, tokenizer):
             piece = tokenizer.id_to_piece(i)
             if len(piece) != 6:
                 print(f"Invalid token: {piece}")
-                sys.exit(1)
+                raise SystemExit(1)
             byte_value = int(piece[3:-1], 16)
             text = struct.pack("B", byte_value)
         else:
diff --git a/convert-gptq-to-ggml.py b/convert-gptq-to-ggml.py
index 42e99c2ff..d4fab656a 100644
--- a/convert-gptq-to-ggml.py
+++ b/convert-gptq-to-ggml.py
@@ -12,7 +12,7 @@ from sentencepiece import SentencePieceProcessor
 
 if len(sys.argv) != 4:
     print("Usage: convert-gptq-to-ggml.py llamaXXb-4bit.pt tokenizer.model out.bin\n")
-    sys.exit(1)
+    raise SystemExit(1)
 
 fname_model = sys.argv[1]
 fname_tokenizer = sys.argv[2]
@@ -57,7 +57,7 @@ for i in range(tokenizer.vocab_size()):
         piece = tokenizer.id_to_piece(i)
         if len(piece) != 6:
             print(f"Invalid token: {piece}")
-            sys.exit(1)
+            raise SystemExit(1)
         byte_value = int(piece[3:-1], 16)
         text = struct.pack("B", byte_value)
     else:
diff --git a/convert-pth-to-ggml.py b/convert-pth-to-ggml.py
index dcef2f6a3..8649bd684 100644
--- a/convert-pth-to-ggml.py
+++ b/convert-pth-to-ggml.py
@@ -16,7 +16,6 @@
 
 import argparse
 import os
-import sys
 import json
 import struct
 import numpy as np
@@ -86,7 +85,7 @@ def get_n_parts(dim):
     n_parts = mappings.get(dim)
     if n_parts is None:
         print(f"Invalid dim: {dim}")
-        sys.exit(1)
+        raise SystemExit(1)
 
     print(f"n_parts = {n_parts}\n")
     return n_parts
@@ -127,7 +126,7 @@ def write_tokens(fout, tokenizer):
             piece = tokenizer.id_to_piece(i)
             if len(piece) != 6:
                 print(f"Invalid token: {piece}")
-                sys.exit(1)
+                raise SystemExit(1)
             byte_value = int(piece[3:-1], 16)
             text = struct.pack("B", byte_value)
         else:
diff --git a/convert-unversioned-ggml-to-ggml.py b/convert-unversioned-ggml-to-ggml.py
index 5151d9081..501fae67e 100644
--- a/convert-unversioned-ggml-to-ggml.py
+++ b/convert-unversioned-ggml-to-ggml.py
@@ -5,7 +5,6 @@ import argparse
 import glob
 import os
 import struct
-import sys
 from sentencepiece import SentencePieceProcessor
 
 HPARAMS = keys = ["vocab_size", "dim", "multiple_of", "n_heads", "n_layers"]
@@ -51,7 +50,7 @@ def write_tokens(fout, tokenizer):
             piece = tokenizer.id_to_piece(i)
             if len(piece) != 6:
                 print(f"Invalid token: {piece}")
-                sys.exit(1)
+                raise SystemExit(1)
             byte_value = int(piece[3:-1], 16)
             text = struct.pack("B", byte_value)
         else: