TheEmperor2/muse-shield-glimmer-er-v3a
Text Generation • Updated • 22
Datasets:
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: CastError
Message: Couldn't cast
uid: string
family: string
text: string
entities: list<item: struct<id: string, type: string, mentions: list<item: list<item: int64>>, subtype: string (... 2 chars omitted)
child 0, item: struct<id: string, type: string, mentions: list<item: list<item: int64>>, subtype: string>
child 0, id: string
child 1, type: string
child 2, mentions: list<item: list<item: int64>>
child 0, item: list<item: int64>
child 0, item: int64
child 3, subtype: string
relations: list<item: null>
child 0, item: null
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': List({'role': Value('string'), 'content': Value('string')})}
because column names don't match
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1835, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 621, in wrapped
for item in generator(*args, **kwargs):
~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 361, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2381, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2309, in cast_table_to_schema
raise CastError(
...<3 lines>...
)
datasets.table.CastError: Couldn't cast
uid: string
family: string
text: string
entities: list<item: struct<id: string, type: string, mentions: list<item: list<item: int64>>, subtype: string (... 2 chars omitted)
child 0, item: struct<id: string, type: string, mentions: list<item: list<item: int64>>, subtype: string>
child 0, id: string
child 1, type: string
child 2, mentions: list<item: list<item: int64>>
child 0, item: list<item: int64>
child 0, item: int64
child 3, subtype: string
relations: list<item: null>
child 0, item: null
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': List({'role': Value('string'), 'content': Value('string')})}
because column names don't match
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 1379, in compute_config_parquet_and_info_response
parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
~~~~~~~~~~~~~~~~~~~~~~~~~^
builder, max_dataset_size_bytes=max_dataset_size_bytes
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 956, in stream_convert_to_parquet
builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1702, in _prepare_split
for job_id, done, content in self._prepare_split_single(
~~~~~~~~~~~~~~~~~~~~~~~~~~^
gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1887, 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.
messages list |
|---|
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
[
{
"role": "system",
"content": "You resolve the people, organisations and private details in a document for a privacy gateway.\nThe document is split into numbered units [n]. Return ONE JSON object and nothing else:\n{\"entities\": [{\"id\": \"...\", \"type\": \"...\", \"role\": \"...\", \"subtype\": \"...\... |
End of preview.
Muse Shield er-v3 training data
This is the data used to train TheEmperor2/muse-shield-glimmer-er-v3a, the local entity-resolution model behind Muse Shield.
Every generated document is fictional. Code plans the people and values, an LLM writes the text with inline tags, code checks and repairs the tags, and a second model pass must agree on owners and references.
| File | What it is |
|---|---|
train-A.jsonl.gz |
The exact training file of the released model: 12,160 chat-format rows, with the v3 system prompt, the document, and the answer as an entity graph. |
val.jsonl.gz |
Validation rows |
generated-v3-families.docs.jsonl |
New generated document families: chat requests, IT tickets, profile forms, schedules |
heldout-*.docs.jsonl |
Held-out sets used to choose the checkpoint, never trained on |
manifest.json |
Counts, sources, and the overlap filtering |
Sources
| Source | Docs |
|---|---|
| er-v2 documents (our generator, relabelled under the v3 policy) | 4,545 |
| New generated families | 3,615 |
| nvidia/Nemotron-PII, train split, converted (CC BY 4.0) | 4,000 |
Decontamination
- Any training text sharing a 12-word run with a benchmark or test text was dropped. The checked sets were the Nemotron-PII test set (500), PUPA, TAB test, and our ER test, challenge and ambiguity sets. This removed 910 er-v2 documents and 169 Nemotron documents.
- Nemotron rows come from the train split only.
Nemotron-PII content is © NVIDIA and used under CC BY 4.0. The generated content is released under CC BY 4.0.
- Downloads last month
- 32
Models trained or fine-tuned on TheEmperor2/muse-shield-er-v3-data