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: TypeError
Message: Couldn't cast array of type
struct<name: string, description: string, parameters: string, required: list<item: string>>
to
{'name': Value('string'), 'description': Value('string'), 'parameters': Json(decode=True)}
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1827, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 613, in wrapped
for item in generator(*args, **kwargs):
~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 343, 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 2378, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2312, in cast_table_to_schema
cast_array_to_feature(
~~~~~~~~~~~~~~~~~~~~~^
table[name] if name in table_column_names else pa.array([None] * len(table), type=schema.field(name).type),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
feature,
^^^^^^^^
)
^
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 1861, in wrapper
return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
~~~~^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2118, in cast_array_to_feature
casted_array_values = _c(array.values, feature.feature)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 1863, in wrapper
return func(array, *args, **kwargs)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2068, in cast_array_to_feature
_c(array.field(name) if name in array_fields else null_array, subfeature)
~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 1863, in wrapper
return func(array, *args, **kwargs)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2158, in cast_array_to_feature
raise TypeError(f"Couldn't cast array of type\n{_short_str(array.type)}\nto\n{_short_str(feature)}")
TypeError: Couldn't cast array of type
struct<name: string, description: string, parameters: string, required: list<item: string>>
to
{'name': Value('string'), 'description': Value('string'), 'parameters': Json(decode=True)}
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 1369, 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 948, 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 1694, 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 1880, 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 | tools list | metadata dict |
|---|---|---|
[
{
"role": "system",
"content": "",
"trainable": false
},
{
"role": "user",
"content": "I need to calculate the total carbon footprint comparison between operating an electric forklift versus a propane-powered one for a full warehouse shift. First, find the average energy consumption of a sta... | [
{
"type": "function",
"function": {
"name": "get_wolfram_results",
"description": "Returns result of wolfram search.",
"parameters": {
"type": "object",
"properties": {
"appid": {
"type": "string",
"description": "Your API key."
}... | {
"domain": "tool_use",
"source": "nvidia/Nemotron-SFT-Agentic-v2:tool_calling"
} |
[
{
"role": "system",
"content": "",
"trainable": false
},
{
"role": "user",
"content": "I want to print 50 copies of a hardcover book with glossy paper through Lulu. However, I'm unsure if the \"premium hardcover\" option includes the glossy paper upgrade. Can you check the product specificat... | [
{
"type": "function",
"function": {
"name": "calculate-print-job-cost",
"description": "Calculate the cost of a print job without creating it",
"parameters": {
"type": "object",
"properties": {
"product_id": {
"type": "string",
"description... | {
"domain": "tool_use",
"source": "nvidia/Nemotron-SFT-Agentic-v2:tool_calling"
} |
[
{
"role": "system",
"content": "",
"trainable": false
},
{
"role": "user",
"content": "I’m overseeing the harvest at my Napa vineyard and need to coordinate the picking crew. Could you tell me the current temperature and weather conditions in Napa, and then provide the forecast for the next ... | [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get current weather conditions for a location in the United States. Perfect for 'What's the weather like in [US location]?' questions. Covers all US states, territories, and coastal waters.",
"parameters": {... | {
"domain": "tool_use",
"source": "nvidia/Nemotron-SFT-Agentic-v2:tool_calling"
} |
[
{
"role": "system",
"content": "",
"trainable": false
},
{
"role": "user",
"content": "I'm designing a technical workshop on water-treatment innovation, and I want to include examples of remote sensing and monitoring technologies used in extreme environments—like those in spaceflight. Could ... | [
{
"type": "function",
"function": {
"name": "get_news_reports_by_id",
"description": "type=4, Search for an report related to spaceflight",
"parameters": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "A unique... | {
"domain": "tool_use",
"source": "nvidia/Nemotron-SFT-Agentic-v2:tool_calling"
} |
[
{
"role": "system",
"content": "",
"trainable": false
},
{
"role": "user",
"content": "I'm trying to update the documentation for our team's JavaScript API, but I need to check if an existing page called \"API Reference\" already covers the fetch() method updates we've been making. Can you f... | [
{
"type": "function",
"function": {
"name": "get-page",
"description": "Returns the standard page object for a wiki page, optionally including page source or rendered HTML, and including the license and information about the latest revision.",
"parameters": {
"type": "object",
... | {
"domain": "tool_use",
"source": "nvidia/Nemotron-SFT-Agentic-v2:tool_calling"
} |
[
{
"role": "system",
"content": "",
"trainable": false
},
{
"role": "user",
"content": "A student is working on a physics problem where a charge of 2.5 Coulombs is subjected to a voltage of 100 volts. What is the electrostatic potential energy in this scenario?",
"trainable": false
},
... | [
{
"type": "function",
"function": {
"name": "potential_energy",
"description": "Calculates the electrostatic potential energy given the charge and voltage.",
"parameters": {
"type": "object",
"properties": {
"charge": {
"type": "number",
"d... | {
"domain": "tool_use",
"source": "nvidia/Nemotron-SFT-Agentic-v2:tool_calling"
} |
[
{
"role": "system",
"content": "",
"trainable": false
},
{
"role": "user",
"content": "I need the current Unix epoch time from the server, but I want it displayed backwards (for example, “1700000000” should become “0000000071”). Could you retrieve the epoch timestamp and then reverse the cha... | [
{
"type": "function",
"function": {
"name": "execute_command",
"description": "Execute any shell command",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Command to execute"
},
... | {
"domain": "tool_use",
"source": "nvidia/Nemotron-SFT-Agentic-v2:tool_calling"
} |
[
{
"role": "system",
"content": "",
"trainable": false
},
{
"role": "user",
"content": "\"I want to analyze how current weather conditions in my city affect my team's productivity. First, I need the current weather data for San Francisco. Then, I want to run a Python script to match this data... | [
{
"type": "function",
"function": {
"name": "run-code",
"description": "Run code snippet and return the result.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Code Snippet"
},
... | {
"domain": "tool_use",
"source": "nvidia/Nemotron-SFT-Agentic-v2:tool_calling"
} |
[{"role":"system","content":"","trainable":false},{"role":"user","content":"\"I'm organizing an outd(...TRUNCATED) | [{"type":"function","function":{"name":"get_live_temp","description":"\n Get live temperature for(...TRUNCATED) | {
"domain": "tool_use",
"source": "nvidia/Nemotron-SFT-Agentic-v2:tool_calling"
} |
[{"role":"system","content":"","trainable":false},{"role":"user","content":"I've been thinking about(...TRUNCATED) | [{"type":"function","function":{"name":"get_trending_tickers","description":"Get latest trending tic(...TRUNCATED) | {
"domain": "tool_use",
"source": "nvidia/Nemotron-SFT-Agentic-v2:tool_calling"
} |
End of preview.
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
ORNITH-CODER-SFT-V1
Coding-specialized SFT dataset.
Domain targets
- math: 25,000
- tool_use: 17,000
- general_coding: 20,000
- agentic_coding: 30,000
- reasoning: 15,000
Maximum target: 107,000 examples.
Ingestion
- No
datasets.load_dataset() - Direct PyArrow Parquet processing
- Direct remote HTTP JSONL streaming
- SQLite SHA-256 global deduplication
- Source-aware schema normalization
Hard limits
- Maximum Parquet file: 1.07 GB
- Maximum Parquet source download: 3.22 GB
- Maximum remote JSONL stream: 2.15 GB
- Maximum rows/source: 100,000
- Maximum JSONL line: 16.0 MB
- Maximum text parsed at once: 2.0 MB
Final statistics
- Valid examples: 223,000
- Tool examples: 70,781
- Reasoning examples: 93,000
- Final size: 3,468.22 MB
- Downloads last month
- 38