label-studio-ml-backend: Run directory undefined specified by model_version doesn't exist

I am trying to run custom model without using docker compose. This is code that I am using to launch the server. But I get an error model_version doesn't exist.

app = init_app(
    model_class=MyModel,
    model_dir=os.environ.get("MODEL_DIR", os.path.dirname(__file__)),
    redis_queue=os.environ.get("RQ_QUEUE_NAME", "default"),
    redis_host=os.environ.get("REDIS_HOST", "localhost"),
    redis_port=os.environ.get("REDIS_PORT", 6379),
)
if __name__ == "__main__":
    app.run(host="localhost", port=9090)

Run directory undefined specified by model_version doesn't exist
Traceback (most recent call last):
  File "/media/idk/idk1/label-studio-ml-backend/label_studio_ml/model.py", line 54, in get_result
    job_result = self.get_result_from_job_id(model_version)
  File "/media/idk/idk1/label-studio-ml-backend/label_studio_ml/model.py", line 107, in get_result_from_job_id
    result = self._get_result_from_job_id(job_id)
  File "/media/idk/idk1/label-studio-ml-backend/label_studio_ml/model.py", line 183, in _get_result_from_job_id
    raise IOError(f'Run directory {job_dir} specified by model_version doesn\'t exist')
OSError: Run directory undefined specified by model_version doesn't exist