Spaces:
Sleeping
Sleeping
Download src/deep_learning/data/wiki/runner.py from yetrun/general-deep-learning: direct link, hf CLI and curl.
- Browser
- Download file 724 Bytes
-
https://huggingface.co/spaces/yetrun/general-deep-learning/resolve/main/src/deep_learning/data/wiki/runner.py
- Command line
-
hf download hf://spaces/yetrun/general-deep-learning/src/deep_learning/data/wiki/runner.py
-
curl -L -o runner.py https://huggingface.co/spaces/yetrun/general-deep-learning/resolve/main/src/deep_learning/data/wiki/runner.py
724 Bytes
| """Wiki 数据集 Runner | |
| Usage: | |
| python data/wiki/runner.py test_dataset | |
| ENV=production python data/wiki/runner.py test_dataset | |
| """ | |
| import pathlib | |
| import sys | |
| sys.path.insert(0, str(pathlib.Path(__file__).parent.parent.parent)) | |
| from deep_learning.data.runner import DatasetRunner | |
| from .dataset import WikiDataset | |
| from deep_learning.env.resolve import resolve_path, resolve_env | |
| dataset = WikiDataset( | |
| data_dir=str( | |
| resolve_env(resolve_path("data/dev/mini_c4"), resolve_path("~/data/wiki/mini_c4")) | |
| ), | |
| tokenizer_type=resolve_env("character", "sentence_piece"), | |
| sequence_length=256, | |
| ) | |
| runner = DatasetRunner( | |
| dataset=dataset, | |
| name="wiki", | |
| ) | |
| if __name__ == "__main__": | |
| runner() | |