Datasets:

adasdadsd
/

Qwen3-Coder-SFT-2.4M

messages list	tools unknown
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "You are tasked with creating a file writer class that can compress and write data to a file in a specific format. The format is a custom compressed file format that uses a block-based compressi...	null
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "Can you create a Python 3 function that\ncompacts JSON according to context." }, { "role": "assistant", "content": "def transform_jsonld(self, obj):\n \"\"\"Compact JSON acco...	null
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "Change the greeting to be more casual" }, { "role": "assistant", "content": "Ok, I will:\n\n1. Switch the greeting text from \"Hello\" to \"Hey\".\n\nshow_greeting.py\n```\nimport s...	null
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "You are given a string `text` consisting of alphabetic characters and possibly spaces. Your task is to implement a function `count_vowels` that returns the total number of vowels present in the...	null
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "Can you tell what is the following Python 3 function doing\ndef _copy_streamflow_values(self):\r\n log('Creating streamflow variable', 'INFO')\r\n q_var = self.cf_nc.createVariabl...	null
[ { "role": "system", "content": "You are an expert Python programmer. Think step by step before writing code." }, { "role": "user", "content": "Please look through a given GitHub issue and repository structure and provide a list of files that one would need to edit or look at to solve the issue.\...	null
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "You are tasked with implementing a Python class that represents a hierarchical structure for supplier groups. The class should be a subclass of `NestedSet` from the `frappe.utils.nestedset` mod...	null
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "You are given a filename, a delimiter, and a number of parts. Your task is to implement a function `process_filename` that splits the filename by the delimiter, removes any empty strings result...	null
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "You are given a dataset represented as a list of tuples, where each tuple corresponds to a row in the dataset. Each row consists of 7 elements, representing different attributes labeled A, B, C...	null
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "You are tasked with implementing a function `convert_to_float` that processes an input value and returns a float. The function should handle various data types and convert them appropriately. S...	null
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "You are tasked with creating a Python class that manages the publication of visualization markers in a ROS (Robot Operating System) environment. The class should handle the creation and publica...	null
[ { "role": "system", "content": "You are an expert Python programmer." }, { "role": "user", "content": "How would you explain what the following Python 3 function does\ndef find(self, path, mode='node'):\n path = path.split('.') if isinstance(path, str) else list(path)\n item = self...	null

End of preview.

Qwen3-Coder SFT Dataset

用于微调 Qwen3-Coder-Next 的 Python 编程 SFT 数据集。

构成

train.jsonl: 2,361,724 条
val.jsonl: 124,302 条
标准 messages 格式（system/user/assistant/tool 角色），部分含 tools 字段
含工具调用 ~7.1%，<think> 推理 ~26%，中文指令 ~13%

格式

{"messages": [{"role": "system", "content": "..."}, {"role": "user", "content": "..."}, {"role": "assistant", "content": "..."}]}

含工具调用的记录额外带 tools 字段（OpenAI function-calling schema）。

加载

from datasets import load_dataset
ds = load_dataset("adasdadsd/Qwen3-Coder-SFT-2.4M", data_files={"train": "train.jsonl", "validation": "val.jsonl"})

Downloads last month: 13

Total file size:

24.4 GB