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<from: string, value: string, more: list<item: struct<from: string, value: string>>>
to
{'from': Value('string'), 'value': Value('string')}
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1872, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 265, 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 120, 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 2272, in table_cast
return cast_table_to_schema(table, schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2224, in cast_table_to_schema
cast_array_to_feature(
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1795, in wrapper
return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2052, in cast_array_to_feature
casted_array_values = _c(array.values, feature.feature)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1797, in wrapper
return func(array, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2092, 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<from: string, value: string, more: list<item: struct<from: string, value: string>>>
to
{'from': Value('string'), 'value': Value('string')}
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 884, in download_and_prepare
self._download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 947, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1739, 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 1922, 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.
conversations list |
|---|
[
{
"from": "human",
"value": "Given that the graph of the power function $y=f(x)$ passes through the point $(2,\\sqrt{2})$.\n(1) Find the analytical expression of the function $y=f(x)$, determine and prove the monotonicity of $y=f(x)$ on $[0,+\\infty)$;\n(2) The function $g(x)$ is an even function on $\\math... |
[
{
"from": "human",
"value": "能否详细解释一下左倾和右倾的概念？"
},
{
"from": "assistant",
"value": "<think>\n嗯，用户问的是左倾和右倾的概念，需要详细解释。首先得确认这两个术语在不同领域的含义差异，因为政治学和计算机科学里都有使用，但意思完全不同。用户可能没意识到这点，所以得先区分清楚。\n\n用户可能是在学习政治或者历史时遇到的，也可能是编程时碰到的。比如在数据结构里，AVL树或者红黑树会提到左倾右倾。但问题里没具体说明，所以得两边都覆盖到，避免用户混淆。\n\n先想政治方面。左倾和右倾在政治中通常指偏离正确... |
[
{
"from": "human",
"value": "Xiao Min sells a product at a 10% discount off the marked price (i.e., a $10\\%$ discount), and still makes a profit of $30$ yuan. If the cost price of this product is $60$ yuan, then the marked price of the product is ____ yuan."
},
{
"from": "assistant",
"value": "... |
[
{
"from": "human",
"value": "1. Let the sequence $\\left\\{a_{n}\\right\\}$ satisfy\n$$\n\\begin{array}{l}\na_{1}=1, a_{2}=4, a_{3}=9, \\\\\na_{n}=a_{n-1}+a_{n-2}-a_{n-3}(n=4,5, \\cdots) .\n\\end{array}\n$$\n\nThen $a_{2011}=$"
},
{
"from": "assistant",
"value": "<think>Okay, so I need to find t... |
[
{
"from": "human",
"value": "What is the purpose of the `collectGifts()` method in the `ServiceAgent` class? Can you explain the algorithm used in this method and how it manages to collect gifts from the given list of gifts with the help of robots?\n\n```java\nimport java.util.*;\n\nenum Size {\n SMALL, ... |
[
{
"from": "human",
"value": "下面说法中, 正确的有 ( ) 个。\n\n(1)一个数的因数的个数是有限的, 一个数的倍数的个数是无限的。(2)任何非零自然数都有因数 1 。 (3) $32 \\div 4=8$, 所以 32 是 4 的倍数。(4)奇数十奇数=奇数。(5) 1 既不是质数, 也不是合数。(6)自然数 $\\mathrm{a}$大于 $b, a$ 的因数个数一定比 $b$ 多。(7)非零自然数按照因数的个数可以分为质数、合数和 1。(8)个位是 $3 、 6 、 9$ 的数, 都是 3 的倍数。\n\nA. 3\nB. 4\nC. 5\nD. 6"
},
{... |
[
{
"from": "human",
"value": "能帮我把这段小说改编成漫画剧本吗？"
},
{
"from": "assistant",
"value": "<think>\n嗯，用户想让我把一段小说改编成漫画剧本。这挺有意思的，不过ta没直接贴出小说内容，可能还没准备好或者不确定怎么操作。\n\n用户可能是刚入门的创作者，手头有小说但没漫画经验，有点无从下手。也可能是专业写手想拓展作品形式。从简洁的提问看，ta可能着急要结果，但没意识到改编需要具体文本——就像让我“做顿饭”却不给食材。\n\n得先解决核心问题：没原文就无法操作。但直接说“你没给内容”太生硬，要引导ta提供素... |
[
{
"from": "human",
"value": "As a data scientist, you are tasked with creating an AI system that can accurately predict a person's mood based on their social media posts. To do this, you use the Python programming language and implement a neural network algorithm. \nYou start by collecting a large dataset o... |
[
{
"from": "human",
"value": "我在学习驾驶时遇到了难题，作为一名29岁的上海XX大学计算机专业外聘讲师，驾校教练对我持续无理谩骂，这让我感到非常困扰。在以往较为和谐的社交环境中未曾遭遇此类委屈，请问我应当选择忍耐，还是通过录音方式取证并考虑提起民事诉讼来维护自身权益？"
},
{
"from": "assistant",
"value": "<think>\n首先，用户的问题是关于他在学习驾驶时遇到的难题。他是一名29岁的上海XX大学计算机专业外聘讲师，驾校教练对他持续无理谩骂，这让他感到困扰。他提到在以往较为和谐的社交环境中未曾遭遇此类委屈，所以他在考虑是... |
[
{
"from": "human",
"value": "You are an AI assistant. User will you give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.\nGenerate a sentence that includes all the following words: motorcycle, row, stand"
},
{
... |
[
{
"from": "human",
"value": "A factory produces widgets, and the quality of each widget is rated on a scale of 0 to 10. However, due to measurement error, it is impossible to rate the quality of a widget with complete certainty. Instead, the factory's quality control department assigns widgets to categories... |
[
{
"from": "human",
"value": "Given $x \\gt 1$, the minimum value of $x+\\frac{1}{{x-1}}$ is ______."
},
{
"from": "assistant",
"value": "<think>Okay, so I need to find the minimum value of the function f(x) = x + 1/(x - 1) where x is greater than 1. Hmm, let's see. I remember from algebra that s... |
[
{
"from": "human",
"value": "某大学有男生4000人，女生人数是男生的(3/5)．这个大学一共有多少个学生？"
},
{
"from": "assistant",
"value": "<think>\n我现在要解决的问题是：某大学有男生4000人，女生人数是男生的3/5，问这个大学一共有多少学生。首先，我需要理清楚题目中的数量关系。首先，男生人数已知是4000人，女生人数是男生的3/5，所以首先应该算出女生的人数，然后再把男生和女生的人数加起来，就是总人数了。\n\n首先，女生人数是男生的3/5，男生有4000人，所以女生人数应该是4000乘以3/5。那计算... |
[
{
"from": "human",
"value": "（2022 春・孟县期中）如果 $a 、 b$ 是两个质数, 那么下面（）的结果一定是合数。\n\nA. $a+b$\nB. $a \\times b$\nC. $a \\div b$"
},
{
"from": "assistant",
"value": "<think>\n我现在要解决这个问题：题目说如果a和b是两个质数，那么下面哪个选项的结果一定是合数。选项是A. a+b，B. a×b，C. a÷b。首先，我需要回忆一下质数和合数的定义。质数是指大于1的自然数，除了1和它本身之外没有其他正因数的数；合数是指除了1和它本身还... |
[
{
"from": "human",
"value": "Solve the following coding problem using the programming language python:\n\nA great king of a certain country suddenly decided to visit the land of a friendly country. The country is famous for trains, and the king visits various stations.\n\nThere are 52 train stations, each w... |
End of preview.
CMB-Eagle-Mix-330k 数据集
数据集简介
CMB-Eagle-Mix-330k包含两个从Qwen3-235B-A22B模型中提取的数据集。一共包含33万条高质量的中英文数据，涵盖了广泛的推理领域，且具有相同的格式。
本数据集的核心目标是为EAGLE-3模型训练，提供一个能够显著提升其效果（如token接受率）的优质语料。实践证明，使用本数据集对 Qwen3-32B 模型进行EAGLE-3训练，效果提升显著。
我们通过混合抽样两个广泛使用的Qwen3蒸馏数据集，并对数据集进行了统一的格式化，创建了这个EAGLE-3训练专用数据集，该数据集中的中英文数据分别来源于以下两个数据集：
在实际使用该数据集进行训练时，建议使用原始数据集针对目标模型（如Qwen3-32B）进行数据合成，并通过数据清洗等方式进一步优化生成数据的质量，再将数据用于EAGLE-3的训练任务
数据来源
| 数据来源 (Source Dataset) | 对话数量 (Number of Conversations) |
|---|---|
| Chinese-Qwen3-235B-Thinking-2507-Distill-data-110k-SFT | 110,000 |
| AM-Qwen3-Distilled | 220,000 |
- Downloads last month
- 23