Bachstelze/smolSynformer
Updated
•
202
Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code: DatasetGenerationError
Exception: ArrowNotImplementedError
Message: Cannot write struct type '_format_kwargs' with no child field to Parquet. Consider adding a dummy child field.
Traceback: Traceback (most recent call last):
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1871, in _prepare_split_single
writer.write_table(table)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/arrow_writer.py", line 621, in write_table
self._build_writer(inferred_schema=pa_table.schema)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/arrow_writer.py", line 442, in _build_writer
self.pa_writer = self._WRITER_CLASS(self.stream, schema)
File "/src/services/worker/.venv/lib/python3.9/site-packages/pyarrow/parquet/core.py", line 1010, in __init__
self.writer = _parquet.ParquetWriter(
File "pyarrow/_parquet.pyx", line 2157, in pyarrow._parquet.ParquetWriter.__cinit__
File "pyarrow/error.pxi", line 154, in pyarrow.lib.pyarrow_internal_check_status
File "pyarrow/error.pxi", line 91, in pyarrow.lib.check_status
pyarrow.lib.ArrowNotImplementedError: Cannot write struct type '_format_kwargs' with no child field to Parquet. Consider adding a dummy child field.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1887, in _prepare_split_single
num_examples, num_bytes = writer.finalize()
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/arrow_writer.py", line 640, in finalize
self._build_writer(self.schema)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/arrow_writer.py", line 442, in _build_writer
self.pa_writer = self._WRITER_CLASS(self.stream, schema)
File "/src/services/worker/.venv/lib/python3.9/site-packages/pyarrow/parquet/core.py", line 1010, in __init__
self.writer = _parquet.ParquetWriter(
File "pyarrow/_parquet.pyx", line 2157, in pyarrow._parquet.ParquetWriter.__cinit__
File "pyarrow/error.pxi", line 154, in pyarrow.lib.pyarrow_internal_check_status
File "pyarrow/error.pxi", line 91, in pyarrow.lib.check_status
pyarrow.lib.ArrowNotImplementedError: Cannot write struct type '_format_kwargs' with no child field to Parquet. Consider adding a dummy child field.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1438, 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 1050, in convert_to_parquet
builder.download_and_prepare(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 925, in download_and_prepare
self._download_and_prepare(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1001, 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 1742, 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 1898, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
_data_files
list | _fingerprint
string | _format_columns
null | _format_kwargs
dict | _format_type
null | _output_all_columns
bool | _split
null |
|---|---|---|---|---|---|---|
[
{
"filename": "data-00000-of-00001.arrow"
}
] | a146441047ca1e66 | null | {} | null | false | null |
Data source: PAWS
Teacher model: unsloth/phi-4-unsloth-bnb-4bit
Data augmentation prompts
input_message = "Explain briefly the key differences and whether the following two sentences are a paraphrase: `"+row["sentence1"]+"`\nand\n`"+row["sentence2"]+"`"
if row["label"] == 0: # not a paraphrase
input_message += "Finally conclude in the end that the two sentences are not a parahrase."
else: # the two sentences are paraphrases
input_message += "Finally conclude in the end that the two sentences are a parahrase."
messages = [
{"role": "system", "content": "You are a helpful paraphrase detection system."},
{"role": "user", "content": input_message},
]
Augmention quality
Sometimes the chain-of-thought isn't completly accurate. E.g. phi-4-unsloth-bnb-4bit can't accuratly spot text differences and states a difference for identical text.
Licensing Information
The dataset may be freely used, although acknowledgment of Google LLC ("Google") as the data source would be appreciated. The dataset is provided "AS IS" without any warranty, express or implied. Google disclaims all liability for any damages, direct or indirect, resulting from using the dataset.
- Downloads last month
- 38