Muennighoff/mbpp · Datasets at Hugging Face
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.
evalplus/mbppplus · Datasets at Hugging Face
like 8 EvalPlus 12 Modalities: Text Formats: parquet Size: < 1K Libraries: Datasets pandas Croissant + 1 License: apache-2.0 Dataset card Data Studio FilesFiles and versions Community 1 Dataset Viewer Auto-converted to Parquet API Embed Data Studio Subset (1) default·378 rows default (378 rows) Split (1) test·378 rows test (378 rows) SQL Console
mbpp · Datasets at Hugging Face
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.
mbpp · Datasets at Hugging Face
45 Tasks: Text2Text Generation Languages: English Multilinguality: monolingual Size Categories: n<1K Language Creators: Annotations Creators: crowdsourcedexpert-generated Source Datasets: original ArXiv: Tags: code-generation License: cc-by-4.0 Dataset card FilesFiles and versions Community 3 Dataset Viewer Auto-converted to Parquet API Subset full (974 rows) sanitized (427 rows) Split train ...
google-research-datasets/mbpp at main - Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
mbpp.py · Muennighoff/mbpp at main - Hugging Face
The MBPP (Mostly Basic Python Problems) dataset consists of around 1,000 crowd-sourced Python programming problems, designed to be solvable by entry level programmers, covering programming
dataset_infos.json · mbpp at main - Hugging Face
{"full": {"description": "The MBPP (Mostly Basic Python Problems) dataset consists of around 1,000 crowd-sourced Python\nprogramming problems, designed to be solvable by entry level programmers, covering programming\nfundamentals, standard library functionality, and so on.
Paper page - Program Synthesis with Large Language Models
Aug 15, 2021 · On both datasets, we find that synthesis performance scales log-linearly with model size. Our largest models, even without finetuning on a code dataset, can synthesize solutions to 59.6 percent of the problems from MBPP using few-shot learning with a …
google-research-datasets/mbpp · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
gabeorlanski/bc-mbpp · Datasets at Hugging Face
Dataset Summary The BabelCode-MBPP (BC-MBPP) dataset converts the MBPP dataset released by Google to 16 programming languages.