{"url":"/dataset/lyra","name":"Lyra","full_name":null,"description_markdown":"Lyra is a dataset for code generation that consists on Python code with embedded SQL. This dataset contains 2,000 carefully annotated database manipulation programs from real usage projects. Each program is paired with both a Chinese comment and an English comment.","description_withheld":null,"homepage":"https://github.com/liangqingyuan/lyra","introduced_date":"2021-08-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/lyra-a-benchmark-for-turducken-style-code","title":"Lyra: A Benchmark for Turducken-Style Code Generation","first_author":"Qingyuan Liang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Lyra"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/d0rj/lyra","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}