mlflow/mlflow · error · MlflowException

INVALID_PARAMETER_VALUE

INVALID_PARAMETER_VALUE

Error message

The provided directory {local_checkpoint_dir} does not contain a config.json file.Please ensure that the directory contains a valid transformers model checkpoint.

What it means

Error "The provided directory {local_checkpoint_dir} does not contain a config.json file.Please ensure that the directory contains a valid transformers model checkpoint." thrown in mlflow/mlflow.

Source

Thrown at mlflow/transformers/flavor_config.py:203

def build_flavor_config_from_local_checkpoint(
    local_checkpoint_dir: str,
    task: str,
    processor=None,
    torch_dtype=None,
) -> dict[str, Any]:
    """
    Generates the flavor metadata from a Hugging Face model repository ID
    e.g. "meta-llama/Meta-Llama-3.1-405B, instead of the pipeline instance in-memory.
    """
    import transformers
    from transformers import AutoTokenizer, pipelines
    from transformers.utils import is_torch_available

    from mlflow.transformers.model_io import _MODEL_BINARY_FILE_NAME

    config_path = os.path.join(local_checkpoint_dir, "config.json")
    if not os.path.exists(config_path):
        raise MlflowException(
            f"The provided directory {local_checkpoint_dir} does not contain a config.json file."
            "Please ensure that the directory contains a valid transformers model checkpoint.",
            error_code=INVALID_PARAMETER_VALUE,
        )

    with open(config_path) as f:
        config = json.load(f)

    task_metadata = pipelines.check_task(task)
    pipeline_class = task_metadata[1]["impl"].__name__

    flavor_conf = {
        FlavorKey.TASK: task,
        FlavorKey.INSTANCE_TYPE: pipeline_class,
        FlavorKey.TORCH_DTYPE: str(torch_dtype) if torch_dtype else None,
        FlavorKey.MODEL_TYPE: config["architectures"][0],
        FlavorKey.MODEL_NAME: local_checkpoint_dir,
        FlavorKey.MODEL_BINARY: _MODEL_BINARY_FILE_NAME,

View on GitHub (pinned to 6a27f2decc)

When it happens

Trigger: Thrown at mlflow/transformers/flavor_config.py:203 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of mlflow/mlflow@6a27f2decc (2026-08-29). Data as JSON: /api/errors/9ba724f50cb946ad. Report an issue: GitHub.