diff --git a/tools/ckpts/convert_hf_to_sequential.py b/tools/ckpts/convert_hf_to_sequential.py
index 3d4f756ed..8a3902bce 100644
--- a/tools/ckpts/convert_hf_to_sequential.py
+++ b/tools/ckpts/convert_hf_to_sequential.py
@@ -14,7 +14,7 @@
 from transformers import GPTNeoXForCausalLM, GPTNeoXConfig
 
 sys.path.append(
-    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir))
+    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir, os.path.pardir))
 )
 from megatron.neox_arguments import NeoXArgs
 from megatron.training import get_model, get_optimizer, get_learning_rate_scheduler
diff --git a/tools/ckpts/convert_module_to_hf.py b/tools/ckpts/convert_module_to_hf.py
index 5a147f218..f3f43c308 100644
--- a/tools/ckpts/convert_module_to_hf.py
+++ b/tools/ckpts/convert_module_to_hf.py
@@ -25,7 +25,7 @@
 
 
 sys.path.append(
-    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir))
+    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir, os.path.pardir))
 )
 from megatron.tokenizer import build_tokenizer
 
diff --git a/tools/ckpts/convert_sequential_to_hf.py b/tools/ckpts/convert_sequential_to_hf.py
index d38184131..f0a505ac3 100644
--- a/tools/ckpts/convert_sequential_to_hf.py
+++ b/tools/ckpts/convert_sequential_to_hf.py
@@ -25,7 +25,7 @@
 from typing import List
 
 sys.path.append(
-    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir))
+    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir, os.path.pardir))
 )
 from megatron.tokenizer import build_tokenizer
 
diff --git a/tools/datasets/merge_datasets.py b/tools/datasets/merge_datasets.py
index c5d1e6255..4239c5eb5 100644
--- a/tools/datasets/merge_datasets.py
+++ b/tools/datasets/merge_datasets.py
@@ -4,7 +4,7 @@
 import argparse
 
 sys.path.append(
-    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir))
+    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir, os.path.pardir))
 )
 
 from megatron.data import indexed_dataset
diff --git a/tools/datasets/preprocess_data.py b/tools/datasets/preprocess_data.py
index 862620eb8..e780bec34 100644
--- a/tools/datasets/preprocess_data.py
+++ b/tools/datasets/preprocess_data.py
@@ -26,7 +26,7 @@
 import numpy as np
 
 sys.path.append(
-    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir))
+    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir, os.path.pardir))
 )
 import time
 import tqdm
diff --git a/tools/datasets/preprocess_data_with_mask.py b/tools/datasets/preprocess_data_with_mask.py
index 83447dd12..093d94b2f 100644
--- a/tools/datasets/preprocess_data_with_mask.py
+++ b/tools/datasets/preprocess_data_with_mask.py
@@ -62,7 +62,7 @@
 import numpy as np
 
 sys.path.append(
-    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir))
+    os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir, os.path.pardir))
 )
 import time
 import tqdm