from datasets import load_dataset
from transformers import AutoModelForSeq2SeqLM
from transformers import AutoTokenizer
from transformers import GenerationConfig
huggingface_dataset_name = “knkarthick/dialogsum”dataset = load_dataset(huggingface_dataset_name)
Traceback (most recent call last):
File “”, line 1, in
File “/opt/conda/lib/python3.9/site-packages/datasets/load.py”, line 1767, in load_dataset
builder_instance = load_dataset_builder(
File “/opt/conda/lib/python3.9/site-packages/datasets/load.py”, line 1498, in load_dataset_builder
dataset_module = dataset_module_factory(
File “/opt/conda/lib/python3.9/site-packages/datasets/load.py”, line 1215, in dataset_module_factory
raise e1 from None
File “/opt/conda/lib/python3.9/site-packages/datasets/load.py”, line 1192, in dataset_module_factory
return HubDatasetModuleFactoryWithoutScript(
File “/opt/conda/lib/python3.9/site-packages/datasets/load.py”, line 765, in get_module
else get_data_patterns_in_dataset_repository(hfh_dataset_info, self.data_dir)
File “/opt/conda/lib/python3.9/site-packages/datasets/data_files.py”, line 675, in get_data_patterns_in_dataset_repository
return _get_data_files_patterns(resolver)
File “/opt/conda/lib/python3.9/site-packages/datasets/data_files.py”, line 236, in _get_data_files_patterns
data_files = pattern_resolver(pattern)
File “/opt/conda/lib/python3.9/site-packages/datasets/data_files.py”, line 486, in _resolve_single_pattern_in_dataset_repository
glob_iter = [PurePath(filepath) for filepath in fs.glob(PurePath(pattern).as_posix()) if fs.isfile(filepath)]
File “/opt/conda/lib/python3.9/site-packages/fsspec/spec.py”, line 606, in glob
pattern = glob_translate(path + (“/” if ends_with_sep else “”))
File “/opt/conda/lib/python3.9/site-packages/fsspec/utils.py”, line 734, in glob_translate
raise ValueError(
ValueError: Invalid pattern: ‘**’ can only be an entire path component
Sorted.
I was not following this.
Activate studio conda environment using “conda activate studio” to install extensions, list extension etc
Can somebody explain what is this conda environment?
Have you tried updating the datasets library. Use following:
pip install -U datasets
datasets with version 2.18.0 I was able to download the data properly.