Improve error logging and documentation for issue 4007

doc/frameworks/pytorch/using_pytorch.rst

@@ -1048,6 +1048,43 @@ see `For versions 1.1 and lower <#for-versions-1.1-and-lower>`_.
 
 Where ``requirements.txt`` is an optional file that specifies dependencies on third-party libraries.
 
+Important Packaging Instructions
+--------------------------------
+
+When creating your model artifact (``model.tar.gz``), follow these steps to avoid common deployment issues:
+
+1. Navigate to the directory containing your model files:
+
+   .. code:: bash
+
+       cd my_model
+
+2. Create the tar archive from within this directory:
+
+   .. code:: bash
+
+       tar czvf ../model.tar.gz *
+
+**Common Mistakes to Avoid:**
+
+* Do NOT create the archive from the parent directory using ``tar czvf model.tar.gz my_model/``.
+  This creates an extra directory level that will cause deployment errors.
+* Ensure ``inference.py`` is directly under the ``code/`` directory in your archive.
+* Verify your archive structure using:
+
+  .. code:: bash
+
+      tar tvf model.tar.gz
+
+  You should see output similar to:
+
+  ::
+
+      model.pth
+      code/
+      code/inference.py
+      code/requirements.txt
+
 Create a ``PyTorchModel`` object
 --------------------------------
 
@@ -1066,6 +1103,15 @@ Now call the :class:`sagemaker.pytorch.model.PyTorchModel` constructor to create
 
 Now you can call the ``predict()`` method to get predictions from your deployed model.
 
+Troubleshooting
+---------------
+
+If you encounter a ``FileNotFoundError`` for ``inference.py``, check:
+
+1. That your model artifact is packaged correctly following the instructions above
+2. The structure of your ``model.tar.gz`` file matches the expected layout
+3. You're creating the archive from within the model directory, not from its parent
+
 ***********************************************
 Attach an estimator to an existing training job
 ***********************************************

src/sagemaker/utils.py

@@ -13,10 +13,12 @@
 """Placeholder docstring"""
 from __future__ import absolute_import
 
+import abc
 import contextlib
 import copy
 import errno
 import inspect
+import json
 import logging
 import os
 import random
@@ -25,31 +27,30 @@
 import tarfile
 import tempfile
 import time
-from functools import lru_cache
-from typing import Union, Any, List, Optional, Dict
-import json
-import abc
 import uuid
 from datetime import datetime
-from os.path import abspath, realpath, dirname, normpath, join as joinpath
-
+from functools import lru_cache
 from importlib import import_module
+from os.path import abspath, dirname
+from os.path import join as joinpath
+from os.path import normpath, realpath
+from typing import Any, Dict, List, Optional, Union
 
 import boto3
 import botocore
 from botocore.utils import merge_dicts
-from six.moves.urllib import parse
 from six import viewitems
+from six.moves.urllib import parse
 
 from sagemaker import deprecations
 from sagemaker.config import validate_sagemaker_config
 from sagemaker.config.config_utils import (
-    _log_sagemaker_config_single_substitution,
     _log_sagemaker_config_merge,
+    _log_sagemaker_config_single_substitution,
 )
 from sagemaker.enums import RoutingStrategy
 from sagemaker.session_settings import SessionSettings
-from sagemaker.workflow import is_pipeline_variable, is_pipeline_parameter_string
+from sagemaker.workflow import is_pipeline_parameter_string, is_pipeline_variable
 from sagemaker.workflow.entities import PipelineVariable
 
 ALTERNATE_DOMAINS = {
@@ -624,7 +625,24 @@
             if os.path.exists(os.path.join(code_dir, inference_script)):
                 pass
             else:
-                raise
+                raise FileNotFoundError(
+                    f"Could not find '{inference_script}'. Common solutions:\n"
+                    "1. Make sure inference.py exists in the code/ directory\n"
+                    "2. Package your model correctly:\n"
+                    "   - ✅ DO: Navigate to the directory containing model files and run:\n"
+                    "     cd /path/to/model_files\n"
+                    "     tar czvf ../model.tar.gz *\n"
+                    "   - ❌ DON'T: Create from parent directory:\n"
+                    "     tar czvf model.tar.gz model/\n"
+                    "\nExpected structure in model.tar.gz:\n"
+                    "   ├── model.pth (or your model file)\n"
+                    "   └── code/\n"
+                    "       ├── inference.py\n"
+                    "       └── requirements.txt\n"
+                    "\nFor more details, see the documentation:\n"
+                    + "https://sagemaker.readthedocs.io/en/stable/"
+                    + "frameworks/pytorch/using_pytorch.html#bring-your-own-model"
+                )
 
     for dependency in dependencies:
         lib_dir = os.path.join(code_dir, "lib")