Beginner needs help load_dataset FileNotFoundError

Hello Everybody,

I am an absolute beginner and I hope you can help me.

I created the RainerGa/openassistant-guanaco-de for finetuning Falcon with only german Language.

But I am getting an Error.

I hope you can help me find my mistake. Thanks a lot!

Rainer

from datasets import load_dataset
dataset_name = “RainerGa/openassistant-guanaco-de”

dataset = load_dataset(dataset_name, split=“train”)


FileNotFoundError Traceback (most recent call last)

in <cell line: 8>()
6 # dataset = load_dataset(dataset_name, split=“train”)
7 dataset_name = “RainerGa/openassistant-guanaco-de”
----> 8 dataset = load_dataset(dataset_name, split=“train”)
9

2 frames

/usr/local/lib/python3.10/dist-packages/datasets/load.py in dataset_module_factory(path, revision, download_config, download_mode, dynamic_modules_path, data_dir, data_files, **download_kwargs)
1225 raise e1 from None
1226 if isinstance(e1, FileNotFoundError):
→ 1227 raise FileNotFoundError(
1228 f"Couldn’t find a dataset script at {relative_to_absolute_path(combined_path)} or any data file in the same directory. "
1229 f"Couldn’t find ‘{path}’ on the Hugging Face Hub either: {type(e1).name}: {e1}"

FileNotFoundError: Couldn’t find a dataset script at /content/RainerGa/openassistant-guanaco-de/openassistant-guanaco-de.py or any data file in the same directory. Couldn’t find ‘RainerGa/openassistant-guanaco-de’ on the Hugging Face Hub either: FileNotFoundError: Dataset ‘RainerGa/openassistant-guanaco-de’ doesn’t exist on the Hub. If the repo is private or gated, make sure to log in with huggingface-cli login.

Hello, looks like load_dataset() script can’t find your dataset/loading script directory. Are you loading a dataset from a folder or using a script? Anyway, datasets library has a good documentation for that purpose. Hope this can help!