Hi all,
I just want to use Google colab to test my code while I suddenly found I cannot load dataset anymore.
The code is pretty simple and I have already login in the notebook.  What should I now?
from datasets import load_dataset
# based on config
raw_datasets = load_dataset("HuggingFaceH4/ultrachat_200k")
TypeError                                 Traceback (most recent call last)
 in <cell line: 4>()
2
3 # based on config
----> 4 raw_datasets = load_dataset(“HuggingFaceH4/ultrachat_200k”)
18 frames
/usr/local/lib/python3.10/dist-packages/datasets/load.py in load_dataset(path, name, data_dir, data_files, split, cache_dir, features, download_config, download_mode, verification_mode, ignore_verifications, keep_in_memory, save_infos, revision, token, use_auth_token, task, streaming, num_proc, storage_options, trust_remote_code, **config_kwargs)
2607
2608     # Download and prepare data
 → 2609     builder_instance.download_and_prepare(
2610         download_config=download_config,
2611         download_mode=download_mode,
/usr/local/lib/python3.10/dist-packages/datasets/builder.py in download_and_prepare(self, output_dir, download_config, download_mode, verification_mode, ignore_verifications, try_from_hf_gcs, dl_manager, base_path, use_auth_token, file_format, max_shard_size, num_proc, storage_options, **download_and_prepare_kwargs)
1025                         if num_proc is not None:
1026                             prepare_split_kwargs[“num_proc”] = num_proc
 → 1027                         self._download_and_prepare(
1028                             dl_manager=dl_manager,
1029                             verification_mode=verification_mode,
/usr/local/lib/python3.10/dist-packages/datasets/builder.py in _download_and_prepare(self, dl_manager, verification_mode, **prepare_split_kwargs)
1098         split_dict = SplitDict(dataset_name=self.dataset_name)
1099         split_generators_kwargs = self._make_split_generators_kwargs(prepare_split_kwargs)
 → 1100         split_generators = self._split_generators(dl_manager, **split_generators_kwargs)
1101
1102         # Checksums verification
/usr/local/lib/python3.10/dist-packages/datasets/packaged_modules/parquet/parquet.py in _split_generators(self, dl_manager)
42             raise ValueError(f"At least one data file must be specified, but got data_files={self.config.data_files}")
43         dl_manager.download_config.extract_on_the_fly = True
—> 44         data_files = dl_manager.download_and_extract(self.config.data_files)
45         if isinstance(data_files, (str, list, tuple)):
46             files = data_files
/usr/local/lib/python3.10/dist-packages/datasets/download/download_manager.py in download_and_extract(self, url_or_urls)
432             extracted_path(s): str, extracted paths of given URL(s).
433         “”"
 → 434         return self.extract(self.download(url_or_urls))
435
436     def get_recorded_sizes_checksums(self):
/usr/local/lib/python3.10/dist-packages/datasets/download/download_manager.py in download(self, url_or_urls)
255         start_time = datetime.now()
256         with stack_multiprocessing_download_progress_bars():
 → 257             downloaded_path_or_paths = map_nested(
258                 download_func,
259                 url_or_urls,
/usr/local/lib/python3.10/dist-packages/datasets/utils/py_utils.py in map_nested(function, data_struct, dict_only, map_list, map_tuple, map_numpy, num_proc, parallel_min_length, batched, batch_size, types, disable_tqdm, desc)
506                 batch_size = max(len(iterable) // num_proc + int(len(iterable) % num_proc > 0), 1)
507             iterable = list(iter_batched(iterable, batch_size))
 → 508         mapped = [
509             _single_map_nested((function, obj, batched, batch_size, types, None, True, None))
510             for obj in hf_tqdm(iterable, disable=disable_tqdm, desc=desc)
/usr/local/lib/python3.10/dist-packages/datasets/utils/py_utils.py in (.0)
507             iterable = list(iter_batched(iterable, batch_size))
508         mapped = [
 → 509             _single_map_nested((function, obj, batched, batch_size, types, None, True, None))
510             for obj in hf_tqdm(iterable, disable=disable_tqdm, desc=desc)
511         ]
/usr/local/lib/python3.10/dist-packages/datasets/utils/py_utils.py in _single_map_nested(args)
394             }
395         else:
 → 396             mapped = [_single_map_nested((function, v, batched, batch_size, types, None, True, None)) for v in pbar]
397             if isinstance(data_struct, list):
398                 return mapped
/usr/local/lib/python3.10/dist-packages/datasets/utils/py_utils.py in (.0)
394             }
395         else:
 → 396             mapped = [_single_map_nested((function, v, batched, batch_size, types, None, True, None)) for v in pbar]
397             if isinstance(data_struct, list):
398                 return mapped
/usr/local/lib/python3.10/dist-packages/datasets/utils/py_utils.py in _single_map_nested(args)
375         and all(not isinstance(v, types) for v in data_struct)
376     ):
 → 377         return [mapped_item for batch in iter_batched(data_struct, batch_size) for mapped_item in function(batch)]
378
379     # Reduce logging to keep things readable in multiprocessing with tqdm
/usr/local/lib/python3.10/dist-packages/datasets/utils/py_utils.py in (.0)
375         and all(not isinstance(v, types) for v in data_struct)
376     ):
 → 377         return [mapped_item for batch in iter_batched(data_struct, batch_size) for mapped_item in function(batch)]
378
379     # Reduce logging to keep things readable in multiprocessing with tqdm
/usr/local/lib/python3.10/dist-packages/datasets/download/download_manager.py in _download_batched(self, url_or_filenames, download_config)
311             )
312         else:
 → 313             return [
314                 self._download_single(url_or_filename, download_config=download_config)
315                 for url_or_filename in url_or_filenames
/usr/local/lib/python3.10/dist-packages/datasets/download/download_manager.py in (.0)
312         else:
313             return [
 → 314                 self._download_single(url_or_filename, download_config=download_config)
315                 for url_or_filename in url_or_filenames
316             ]
/usr/local/lib/python3.10/dist-packages/datasets/download/download_manager.py in _download_single(self, url_or_filename, download_config)
321             # append the relative path to the base_path
322             url_or_filename = url_or_path_join(self._base_path, url_or_filename)
 → 323         out = cached_path(url_or_filename, download_config=download_config)
324         out = tracked_str(out)
325         out.set_origin(url_or_filename)
/usr/local/lib/python3.10/dist-packages/datasets/utils/file_utils.py in cached_path(url_or_filename, download_config, **download_kwargs)
199     if is_remote_url(url_or_filename):
200         # URL, so get it from the cache (downloading if necessary)
 → 201         output_path = get_from_cache(
202             url_or_filename,
203             cache_dir=cache_dir,
/usr/local/lib/python3.10/dist-packages/datasets/utils/file_utils.py in get_from_cache(url, cache_dir, force_download, proxies, etag_timeout, resume_download, user_agent, local_files_only, use_etag, max_retries, token, use_auth_token, ignore_url_params, storage_options, download_desc, disable_tqdm)
674                 ftp_get(url, temp_file)
675             elif scheme not in (“http”, “https”):
 → 676                 fsspec_get(
677                     url, temp_file, storage_options=storage_options, desc=download_desc, disable_tqdm=disable_tqdm
678                 )
/usr/local/lib/python3.10/dist-packages/datasets/utils/file_utils.py in fsspec_get(url, temp_file, storage_options, desc, disable_tqdm)
383         }
384     )
 → 385     fs.get_file(path, temp_file.name, callback=callback)
386
387
/usr/local/lib/python3.10/dist-packages/huggingface_hub/hf_file_system.py in get_file(self, rpath, lpath, callback, outfile, **kwargs)
632         callback.set_size(expected_size)
633         try:
 → 634             http_get(
635                 url=hf_hub_url(
636                     repo_id=resolve_remote_path.repo_id,
TypeError: http_get() got an unexpected keyword argument ‘displayed_filename’
