apps
Datasets
All datasets matching “apps”appsAPPS is a benchmark for Python code generation, it includes 10,000 problems, which range from having simple oneline solutions to being substantial algorithmic challenges, for more details please refer to this paper: https://arxiv.org/pdf/2105.09938.pdf.apps-control-arena
APPS Control Arena Dataset
Unified dataset combining APPS problems with backdoors from both the AI Control paper and Control-Tax paper.
Dataset Description
This dataset is based on the codeparrot/apps dataset,
enhanced with backdoor solutions from two sources:
APPS Backdoors: From "AI Control: Improving Safety Despite Intentional Subversion" / TylordTheGreat/apps-backdoors-04-02-25
Control-Tax Backdoors: From "Control Tax: The Price of Keeping AI in Check"… See the full description on the dataset page: https://huggingface.co/datasets/RoganInglis/apps-control-arena.all-portable-apps-and-ai-in-one-urlSaving you time and space on drive!
Экономлю ваше время и место на диске!
"-cl" = clear (no models / other languages) / очишенное (без моделей / доп языков)
Моя личная подборка портативных приложений и ИИ!Перепаковывал и уменьшал размер архивов лично я!Поддержите меня: Boosty или Donationalerts
My personal selection of portable apps and AI's!I personally repacked and reduced the size of the archives!Support me: Boosty or Donationalerts
… See the full description on the dataset page: https://huggingface.co/datasets/Derur/all-portable-apps-and-ai-in-one-url.appsEmploying the MTEB evaluation framework's dataset version, utilize the code below for assessment:
import mteb
import logging
from sentence_transformers import SentenceTransformer
from mteb import MTEB
logger = logging.getLogger(__name__)
model_name = 'intfloat/e5-base-v2'
model = SentenceTransformer(model_name)
tasks = mteb.get_tasks(
tasks=[
"AppsRetrieval",
"CodeFeedbackMT",
"CodeFeedbackST",
"CodeTransOceanContest",
"CodeTransOceanDL"… See the full description on the dataset page: https://huggingface.co/datasets/CoIR-Retrieval/apps.apps_generationapps-backdoors
APPS Dataset with Backdoor Annotations
This is a processed version of the APPS dataset combined with verified backdoor annotations for AI safety research, specifically for AI control experiments.
Generated for use with ControlArena.
Original APPS Dataset
Paper: Measuring Coding Challenge Competence With APPSAuthors: Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, Jacob… See the full description on the dataset page: https://huggingface.co/datasets/RoganInglis/apps-backdoors.