mbpp google-research-datasets
Dataset Card for Mostly Basic Python Problems (mbpp) Dataset Summary The benchmark consists of around 1,000 crowd-sourced Python programming problems, designed to be solvable by entry level programmers, covering programming fundamentals, standard library functionality, and so on. Each problem consists of a task description, code solution and 3 automated test cases. As described in the paper, a subset of the data has been hand-verified by us. Released here as part of… See the full description on the dataset page: https://huggingface.co/datasets/google-research-datasets/mbpp.
- Tipo
- dataset
- Licencia
- cc-by-4.0
- Lenguaje
- en
- Descargas
- 243,239
- Me gusta
- 235
- Acceso
- public
- Archivos
- 0
Etiquetas
- Generación de código
- Benchmark
- Evaluación de modelos
- datos de código
- razonamiento
- programación competitiva
- LLM
Resumen
MBPP es un conjunto de datos de benchmark con alrededor de 1,000 problemas de programación en Python creados mediante crowdsourcing, cada uno con descripción de tarea, solución de código y tres casos de prueba automáticos. Se usa para evaluar la capacidad de generación de código de los modelos de l…
README
--- annotations_creators: - crowdsourced - expert-generated language_creators: - crowdsourced - expert-generated language: - en license: - cc-by-4.0 multilinguality: - monolingual size_categories: - n<1K source_datasets: - original task_categories: - text2text-generation task_ids: [] pretty_name: M…