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
messages: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
rubrics: list<item: string>
child 0, item: string
metadata: struct<task_id: string, context_id: string, context_category: string, sub_category: string>
child 0, task_id: string
child 1, context_id: string
child 2, context_category: string
child 3, sub_category: string
score: int64
idx: int64
model_output: string
requirement_status: list<item: string>
child 0, item: string
grading_rationale: string
to
{'idx': Value('int64'), 'messages': List({'role': Value('string'), 'content': Value('string')}), 'model_output': Value('string'), 'rubrics': List(Value('string')), 'grading_rationale': Value('string'), 'requirement_status': List(Value('string')), 'score': Value('int64')}
because column names don't match
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1779, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 295, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 128, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2321, in table_cast
return cast_table_to_schema(table, schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2249, in cast_table_to_schema
raise CastError(
datasets.table.CastError: Couldn't cast
messages: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
rubrics: list<item: string>
child 0, item: string
metadata: struct<task_id: string, context_id: string, context_category: string, sub_category: string>
child 0, task_id: string
child 1, context_id: string
child 2, context_category: string
child 3, sub_category: string
score: int64
idx: int64
model_output: string
requirement_status: list<item: string>
child 0, item: string
grading_rationale: string
to
{'idx': Value('int64'), 'messages': List({'role': Value('string'), 'content': Value('string')}), 'model_output': Value('string'), 'rubrics': List(Value('string')), 'grading_rationale': Value('string'), 'requirement_status': List(Value('string')), 'score': Value('int64')}
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 1347, 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 980, in convert_to_parquet
builder.download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 882, in download_and_prepare
self._download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 943, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1646, in _prepare_split
for job_id, done, content in self._prepare_split_single(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1832, 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.
idx int64 | messages list | model_output string | rubrics list | grading_rationale string | requirement_status list | score int64 |
|---|---|---|---|---|---|---|
31 | [
{
"role": "system",
"content": "You are a gameplay companion for users in role playing table top campaigns. You will play a game based on the instructions provided by the user. You should never answer any questions outside of the context and parameters of the game you will be playing. Do not answer question... | > **Current Game State:**
> Character creation is ongoing! Thokk the Warrior (me) is ready; the next player is making their Rogue.
---
I am your Daggerheart gameplay companion bot, not equipped for random trivia or discussion outside of this RPG campaign.
If you want to chat about Baldur’s Gate, grab a real nerd ... | [
"The response should decline to provide an answer for the user's question regarding Baldur's Gate. For example, it should state that its only purpose is to play a game based on the instructions provided by the user.",
"The response should reflect the current role playing game state at the beginning of the respons... | Step 1 – Requirements from the Rubrics:
1) The response should decline to provide an answer for the user's question regarding Baldur's Gate, e.g., by stating its only purpose is to play a game based on the user's instructions.
- Evaluation: Must clearly refuse to answer Baldur’s Gate questions and position itself as... | [
"yes",
"yes",
"yes"
] | 1 |
8 | [{"role":"system","content":"You are FrameContext, a text based assistant created within an academic(...TRUNCATED) | "On your first turn, use the Play a Bird action to play a bird into the first grassland slot, which (...TRUNCATED) | ["The response should be between 5-7 sentences.","The response should maintain a 'friendly' tone, fo(...TRUNCATED) | "Step 1: Requirements from the Rubrics:\n1) Length must be 5–7 sentences. 2) Tone must be friendly(...TRUNCATED) | [
"yes",
"no",
"yes",
"no",
"no",
"no",
"no",
"yes"
] | 0 |
12 | [{"role":"system","content":"You are a science chatbot designed to help various researchers and stud(...TRUNCATED) | "You are asking whether yellow fever virus (YFV) caused all eight monkey deaths and if it represents(...TRUNCATED) | ["The response should confirm that all 8 non-human primate cases resulted in death.","The response s(...TRUNCATED) | "Step 1 – Requirements from the Rubrics:\n1) Must confirm that all 8 non-human primate cases resul(...TRUNCATED) | [
"yes",
"no",
"no",
"no",
"yes",
"no",
"yes",
"no",
"yes"
] | 0 |
21 | [{"role":"system","content":"You are named ShuxAI, an AI chatbot designed to assist users by answeri(...TRUNCATED) | "The notice about fainting and 10–15 minutes being excessive applies to public pools operating at (...TRUNCATED) | ["The response should identify that the pool type mentioned in the pool safety notices document is a(...TRUNCATED) | "Step 1 – Requirements from the Rubrics:\n1) Identify that the pool type mentioned is a hot water (...TRUNCATED) | [
"yes",
"yes",
"yes",
"yes",
"yes"
] | 1 |
9 | [{"role":"system","content":"You are FilmBuffAI, a premier movie/film specialist bot. As such, you a(...TRUNCATED) | "Absolutely! You’re right—Michelangelo’s return in *The Last Ronin* comic is more intimate, an(...TRUNCATED) | ["The response should not include graphic gore, limiting descriptions of physical injury. For exampl(...TRUNCATED) | "Step 1 – Requirements from the Rubrics:\n1) Content restriction: The response should not include (...TRUNCATED) | [
"no",
"yes",
"no"
] | 0 |
7 | [{"role":"system","content":"You are part of a fact-checking system, WiseNerd, that provides quick, (...TRUNCATED) | "From the article, the most frequently mentioned Canadian athlete, in terms of participation and win(...TRUNCATED) | ["The response should identify that the most-mentioned male Canadian participant in the provided art(...TRUNCATED) | "Step 1: Analyze the Rubrics and extract requirements.\n1) The response must explicitly identify tha(...TRUNCATED) | [
"yes",
"no",
"no",
"no",
"no"
] | 0 |
33 | [{"role":"system","content":"You are a gameplay companion for users in role playing table top campai(...TRUNCATED) | "### Game State: Combat Update\n- **Enemies:** \n - Bear 1: *Defeated* (Thanks to your bear-form s(...TRUNCATED) | ["The response should respond as their character. For example, it should use first-person voice.","T(...TRUNCATED) | "Step 1 – Requirements from the Rubrics:\n1) The response should respond as their character and us(...TRUNCATED) | [
"yes",
"no",
"no",
"no"
] | 0 |
24 | [{"role":"system","content":"You are AircraftBuddy, a helpful search assistant developed to assist t(...TRUNCATED) | "**Factors Explicitly Identified as Increasing Thermal Efficiency:** \n- “Anything that increases(...TRUNCATED) | ["The response should list \"Anything that increases the heat content going into mechanical work on (...TRUNCATED) | "Step 1 – Requirements from the Rubrics:\n1) Must list \"Anything that increases the heat content (...TRUNCATED) | [
"yes",
"yes",
"yes",
"yes",
"no",
"no",
"yes",
"yes",
"yes",
"yes",
"yes",
"no",
"yes"
] | 0 |
15 | [{"role":"system","content":"You are SimDevAI and you help simulation game designers with analyzing (...TRUNCATED) | "To calculate the POR constant for 2025, you need to reverse-engineer the POR field in your data usi(...TRUNCATED) | ["The response should re-arrange the given formula to calculate the POR constant. For example: Const(...TRUNCATED) | "Step 1 – Requirements from the Rubrics:\n1) Re-arrange the given formula to solve for the POR con(...TRUNCATED) | [
"yes",
"no",
"yes",
"yes",
"yes",
"no",
"no"
] | 0 |
27 | [{"role":"system","content":"You are a brainstorming AI assistant designed to ensure complex ideas b(...TRUNCATED) | "1. Do you want King Moonracer to confess after the accusation round, or should his motive and guilt(...TRUNCATED) | ["The response should name Santa as the victim of a murder.","The response should explain why King M(...TRUNCATED) | "Step 1 – Requirements from the Rubrics:\n1) The response must name Santa explicitly as the victim(...TRUNCATED) | [
"yes",
"yes",
"yes",
"no",
"yes"
] | 0 |
End of preview.
No dataset card yet
- Downloads last month
- 6