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
source: string
n: int64
seed: int64
sampler: string
line_indices_sha256: string
rendered_text_sha256: string
template: string
text: string
to
{'text': 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 1816, 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 2369, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2297, in cast_table_to_schema
raise CastError(
...<3 lines>...
)
datasets.table.CastError: Couldn't cast
source: string
n: int64
seed: int64
sampler: string
line_indices_sha256: string
rendered_text_sha256: string
template: string
text: string
to
{'text': 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 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 1683, 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 1869, 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.
text string |
|---|
<|im_start|>user
Tool available:
[1] Python interpreter
When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment.
Solve the following math problem step-by-step.
a and b can do a work in 12 days and 36 days respectively . if they work on alternate days begi... |
<|im_start|>user
Tool available:
[1] Python interpreter
When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment.
Solve the following math problem step-by-step.
Norma has 88 cards. She loses 70. So, Norma would have _____ cards .<|im_end|>
<|im_start|>assi... |
<|im_start|>user
My question: Does the following sentence make sense?
"Johnny Carson could be seen on television several times a week in his heyday."
Options:
- yes
- no
Please think gradually:<|im_end|>
<|im_start|>assistant
<think>
Thinking Process:
1. **Analyze the Request:**
* Input sentence: "Johnny Carson... |
<|im_start|>user
Can you write me guidelines on when to use a gif vs a screenshot in technical documentation? Your response must reference a specific date in the future.<|im_end|>
<|im_start|>assistant
<think>
Thinking Process:
1. **Analyze the Request:**
* Topic: Guidelines on using GIFs vs. screenshots in tec... |
<|im_start|>user
Please provide a step-by-step guide on how to use Google Analytics for attribution analysis, including how to access the attribution reports, understand the data, and make informed decisions based on the insights obtained. Use clear and concise language, and include relevant screenshots or visuals to i... |
<|im_start|>user
Write Python code to solve the task.
So you've found a meeting room - phew! You arrive there ready to present, and find that someone has taken one or more of the chairs!! You need to find some quick.... check all the other meeting rooms to see if all of the chairs are in use.
Your meeting room can tak... |
<|im_start|>user
An urn contains $4$ green balls and $6$ blue balls. A second urn contains X green balls and $N$ blue balls. A single ball is drawn at random from each urn. The probability that both balls are of the same color is $0.58$. Find $N$.
If we know the answer to the above question is 144, what is the value o... |
<|im_start|>user
Tool available:
[1] Python interpreter
When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment.
Solve the following math problem step-by-step.
In triangle $ABC$, we have $\angle A = 90^\circ$ and $\sin B = \frac{4}{7}$. Find $\cos C$.<|i... |
<|im_start|>user
At a certain rate percent on simple interest, some amount will amount to Rs. 950 in 5 years. The rate is 5.333333333333333%. What is the initial amount?<|im_end|>
<|im_start|>assistant
<think>
Here's a thinking process that leads to the solution:
1. **Analyze the Request:**
* **Given:**
... |
<|im_start|>user
Tool available:
[1] Python interpreter
When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment.
Solve the following math problem step-by-step.
Lincoln realizes that every time the clock ticks 7 o clock, he is in a train either going to of... |
<|im_start|>user
Show me the C# rendition of this code:
import itertools as it
def is_prime(n):
if n == 1 or n == 0:
return False
else:
for i in range(2, int(n**0.5) + 1):
if n % i == 0:
return False
return True
def has_odd_digits(n):
num_digits = len(st... |
<|im_start|>user
Jason is tired of the neighborhood animals raiding his trash. He pepper-sprays some raccoons and 6 times as many squirrels. If he pepper-sprays x animals total, He pepper-sprays 12 raccoons. What is the value of unknown variable x?<|im_end|>
<|im_start|>assistant
<think>
Here's my thought process for s... |
<|im_start|>user
When 4 times the number is added to some times the number, the result is 55. The number is 5.0. What is the multiplier for the second part of the equation?<|im_end|>
<|im_start|>assistant
<think>
Here's my thought process for solving this word problem:
1. **Analyze the Request:**
* **Given:**
... |
<|im_start|>user
Show me an example of a post request in javascript. Provide a summary of key points at the end.<|im_end|>
<|im_start|>assistant
<think>
The user wants me to show an example of a POST request in JavaScript and provide a summary of key points at the end. I should cover both traditional approaches and mod... |
<|im_start|>user
Develop a cross-platform mobile application using React Native framework that seamlessly integrates with Google Maps API and offers location-based services like real-time traffic updates, finding nearby places of interest, and navigating routes. Design the user interface with a modern, intuitive layout... |
<|im_start|>user
Solve the following math problem step-by-step.
Simplify your answer as much as possible. Present your final answer as \boxed{Your Answer}.
What is the sum of $\left(\dfrac{1}{3}\right) + \left(\dfrac{1}{3}\right)^2 + \left(\dfrac{1}{3}\right)^3 + \left(\dfrac{1}{3}\right)^4$?<|im_end|>
<|im_start|>assi... |
<|im_start|>user
A window is made up of 8 glass panes. Each pane has a length of 12 inches and a width of 8 inches. What is the area of the window?<|im_end|>
<|im_start|>assistant
<think>
Here's my thought process for solving this word problem:
1. **Analyze the Request:**
* **Given:** A window.
* **Compos... |
End of preview.
QATFactory GPTQ calibration set (calib_512)
This calibration dataset is a chosen subset of OpenPerfectBlend.
Concretely: 512 rows sampled with random.Random(42).sample(range(n_rows), 512)
(then sorted) from openperfectblend_100k_Qwen3.5-9B_think_train.jsonl — a
100K-example OpenPerfectBlend prompt set whose responses (including
<think> reasoning traces) were generated by Qwen/Qwen3.5-9B. Each row is
the conversation rendered with the model's stock chat template
(add_generation_prompt=False) into a single text field.
Fingerprints (from calib_512.meta.json)
calib_512.jsonlmd5:d1ff8cce1d785f8e51b71eb237fb7a71- line-indices sha256:
966f4780c1438ebd35c0feaf6dddd258b65fc5e20b44c5b434906dcb7cac4084 - rendered-text sha256:
52d75ac687cc4acca8b220f9f67009ac754dea60fc564bea364e46755abac5c2
Used by
GPTQ PTQ baselines of the QATFactory W4A4 study (llm-compressor 0.12.0
GPTQModifier, max_seq_length=8192, num_calibration_samples=512):
Reproduction scripts: gptq_27b.py / gptq_9b.py (togethercomputer/weilix
branch weili/qat, experiments/w4a4-qwen35-27b/jbom/ and
experiments/mxfp4-qwen35-9b/). Result tables:
qatfactory-experiments.
- Downloads last month
- 29