Datasets:

yuyijiong
/

Long-Instruction-with-Paraphrasing

Tasks:

Text Generation

Languages:

Chinese

English

ArXiv:

License:

Dataset card Data Studio Files Files and versions

xet

Community

Dataset Preview

Duplicate

Split (1)

train

The full dataset viewer is not available (click to read why). Only showing a preview of the rows.

The dataset generation failed because of a cast error

Error code:   DatasetGenerationCastError
Exception:    DatasetGenerationCastError
Message:      An error occurred while generating the dataset

All the data files must have the same columns, but at some point there are 3 new columns ({'QA_new', 'input_ids_len', 'QA'})

This happened while the json dataset builder was generating data using

zip://╨┬░µ▒╛-╠ß╜╗-╔╛│²╘¡╬─╕┤╩÷/single_doc_qa_en_no_paraphrasing.json::/tmp/hf-datasets-cache/medium/datasets/55597974511431-config-parquet-and-info-yuyijiong-Long-Instructio-3f86de7d/downloads/d12c5beee3dc3fb7226abc7eb237e6062bcd6e8701c41c1b9de474f735004336

Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)
Traceback:    Traceback (most recent call last):
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 2011, in _prepare_split_single
                  writer.write_table(table)
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/arrow_writer.py", line 585, in write_table
                  pa_table = table_cast(pa_table, self._schema)
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2302, in table_cast
                  return cast_table_to_schema(table, schema)
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2256, in cast_table_to_schema
                  raise CastError(
              datasets.table.CastError: Couldn't cast
              QA: list<item: struct<question: string, answer: string>>
                child 0, item: struct<question: string, answer: string>
                    child 0, question: string
                    child 1, answer: string
              input_ids_len: int64
              QA_new: list<item: struct<question: string, answer: string>>
                child 0, item: struct<question: string, answer: string>
                    child 0, question: string
                    child 1, answer: string
              messages: list<item: struct<role: string, content: string>>
                child 0, item: struct<role: string, content: string>
                    child 0, role: string
                    child 1, content: string
              to
              {'messages': [{'role': Value(dtype='string', id=None), 'content': Value(dtype='string', id=None)}]}
              because column names don't match
              
              During handling of the above exception, another exception occurred:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1323, in compute_config_parquet_and_info_response
                  parquet_operations = convert_to_parquet(builder)
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 938, in convert_to_parquet
                  builder.download_and_prepare(
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1027, in download_and_prepare
                  self._download_and_prepare(
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1122, in _download_and_prepare
                  self._prepare_split(split_generator, **prepare_split_kwargs)
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1882, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 2013, in _prepare_split_single
                  raise DatasetGenerationCastError.from_cast_error(
              datasets.exceptions.DatasetGenerationCastError: An error occurred while generating the dataset
              
              All the data files must have the same columns, but at some point there are 3 new columns ({'QA_new', 'input_ids_len', 'QA'})
              
              This happened while the json dataset builder was generating data using
              
              zip://╨┬░µ▒╛-╠ß╜╗-╔╛│²╘¡╬─╕┤╩÷/single_doc_qa_en_no_paraphrasing.json::/tmp/hf-datasets-cache/medium/datasets/55597974511431-config-parquet-and-info-yuyijiong-Long-Instructio-3f86de7d/downloads/d12c5beee3dc3fb7226abc7eb237e6062bcd6e8701c41c1b9de474f735004336
              
              Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

messages list
[ { "role": "user", "content": "Chapter: \"Mine ear is open, and my heart prepared:\n The worst is worldly loss thou canst unfold:\n Say, is my kingdom lost?\"\n\n SHAKESPEARE.\n\nIt was a feature peculiar to the colonial wars of North America, that\nthe toils and dangers of the wilderness were to be encounte...
[ { "role": "user", "content": "Chapter: \"They do not sleep.\n On yonder cliffs, a grisly band,\n I see them sit.\"\n\n GRAY.\n\n\"'Twould be neglecting a warning that is given for our good, to lie hid\nany longer,\" said Hawkeye, \"when such sounds are raised in the forest!\nThe gentle ones may keep close, ...
[ { "role": "user", "content": "Chapter: \"I fear we shall outsleep the coming morn\n As much as we this night have overwatched!\"\n\n _Midsummer Night's Dream._\n\nThe instant the shock of this sudden misfortune had abated, Duncan began\nto make his observations on the appearance and proceedings of their\nca...
[{"role":"user","content":"Chapter: \"I'll seek a readier path.\"\n\n PARNELL.\n\nThe route taken by(...TRUNCATED)
[{"role":"user","content":"Chapter: \"Why, anything:\n An honorable murderer, if you will;\n For nau(...TRUNCATED)
[{"role":"user","content":"Chapter: \"Land of Albania! let me bend mine eyes\n On thee, thou rugged (...TRUNCATED)
[{"role":"user","content":"Chapter: \"But though the beast of game\n The privilege of chase may clai(...TRUNCATED)
[{"role":"user","content":"Chapter: \"Brief, I pray you; for you see, 'tis a busy time with me.\"\n\(...TRUNCATED)
[{"role":"user","content":"Chapter: \"But plagues shall spread, and funeral fires increase,\n Till t(...TRUNCATED)
[{"role":"user","content":"Chapter: \"They fought, like brave men, long and well,\n They piled that (...TRUNCATED)

End of preview.

🔥 Updates

[2024.6.4] Add a slim version. The sample number is reduced from about 20k to 10k.

[2024.5.28]

The data format is converted from "chatml" to "messages", which is more convenient to use tokenizer.apply_chat_template. The old version has been moved to "legacy" branch.
The version without "Original text paraphrasing" is added.