embedding-benchmark/DS1000 download history
embedding-benchmark/DS1000 is a text retrieval dataset on the Hugging Face Hub. In the last 30 days it was downloaded 378 times (60 in the last 7 days), and 9,242 times in total. It ranks #41,103 among datasets by monthly downloads.
DS-1000 is a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas. It employs multi-criteria evaluation metrics, including functional correctness and surface-form constraints, resulting in a high-quality dataset with only 1.8% inco