# Code Retrieval for Hugging Face Transformers — Data

来源：https://www.kaggle.com/competitions/code-retrieval-for-hugging-face-transformers/data

采集时间：2026-10-24T10:59:57Z

This dataset consists of natural language questions about the [Hugging Face Transformers](https://github.com/huggingface/transformers) library, together with the file names of 1-3 relevant documents that can help answer the question. All documents associated with a query are equally relevant, and their order in the list is irrelevant.

The dataset was created by [Storia AI](https://storia.ai/) in collaboration with [Morph Labs](https://morph.so/).

## Files

*   **train.csv** - The training set. Consists of 700 pairs of natural language questions and relevant file names.
*   **test.csv** - The test set. Consists of 300 natural language questions.
*   **sample_submission.csv** - A sample submission file in the correct format (with fake documents).

## Columns

*   `id` - A unique identifier for the data instance.
*   `question` - A question in natural language.
*   `documents` - A list of relevant documents, encoded as a JSON string. Each document is represented by the file path in the [Hugging Face Transformers](https://github.com/huggingface/transformers) repository, including the `huggingface/transformers` prefix.