sourcegraph/swe-bench-autocomplete-multiline-eval
收藏Hugging Face2024-07-22 更新2024-07-22 收录
下载链接：
https://hf-mirror.com/datasets/sourcegraph/swe-bench-autocomplete-multiline-eval
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含多个字段，如repo、instance_id、base_commit、patch等，每个字段都有明确的数据类型。数据集还包含一个名为selected_patch的复杂结构，该结构包含多个子字段，如comments、content、file_path等。此外，数据集还包含一个名为all_addition_patch的列表结构，以及一个名为patch_function的结构。数据集的分割信息显示，训练集包含413个样本，总大小为78464960字节。
The dataset contains multiple fields such as repo, instance_id, base_commit, patch, etc., each with a specific data type. The dataset also includes a complex structure named selected_patch, which contains multiple subfields such as comments, content, file_path, etc. Additionally, the dataset includes a list structure named all_addition_patch and a structure named patch_function. The split information shows that the training set contains 413 samples with a total size of 78464960 bytes.
提供机构：
sourcegraph
