diff --git a/convert-gptneox-hf-to-gguf.py b/convert-gptneox-hf-to-gguf.py
index e6c3d6935..95704ec43 100755
--- a/convert-gptneox-hf-to-gguf.py
+++ b/convert-gptneox-hf-to-gguf.py
@@ -131,7 +131,7 @@ tokenizer = AutoTokenizer.from_pretrained(dir_model)
 reverse_vocab = {id: encoded_tok for encoded_tok, id in tokenizer.vocab.items()}
 
 for i in range(vocab_size):
-    tokens.append(reverse_vocab[i])
+    tokens.append(reverse_vocab[i] if i in reverse_vocab else f"[PAD{i}]")
     scores.append(0.0) # dummy
     toktypes.append(gguf.TokenType.NORMAL)
 
diff --git a/convert-starcoder-hf-to-gguf.py b/convert-starcoder-hf-to-gguf.py
index 90c3b5057..9d13637ce 100755
--- a/convert-starcoder-hf-to-gguf.py
+++ b/convert-starcoder-hf-to-gguf.py
@@ -121,7 +121,7 @@ tokenizer = AutoTokenizer.from_pretrained(dir_model)
 reverse_vocab = {id: encoded_tok for encoded_tok, id in tokenizer.vocab.items()}
 
 for i in range(vocab_size):
-    tokens.append(reverse_vocab[i])
+    tokens.append(reverse_vocab[i] if i in reverse_vocab else f"[PAD{i}]")
     scores.append(0.0) # dummy
     toktypes.append(gguf.TokenType.NORMAL)