datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
cqadupstack-unix
CQADupstackUnixRetrieval
An MTEB dataset
Massive Text Embedding Benchmark
CQADupStack: A Benchmark Data Set for Community Question-Answering Research
Task category
t2t
Domains
Written, Web, Programming
Reference
http://nlp.cis.unimelb.edu.au/resources/cqadupstack/
How to evaluate on this task
You can evaluate an embedding model on this dataset using the following code:
import mteb
task = mteb.get_tasks(["CQADupstackUnixRetrieval"])
evaluator =… See the full description on the dataset page: https://huggingface.co/datasets/mteb/cqadupstack-unix.unix-commands
Unix Commands Dataset
Description
The Unix Commands Dataset is a unique collection of real-world Unix command line examples, captured from various system prompts representing different user roles and responsibilities, such as system administrators, DevOps, network administrators, Docker administrators, regular users, and hackers.
The dataset consists of Unix commands ranging from basic to advanced levels and from a wide array of categories, including file operations (ls… See the full description on the dataset page: https://huggingface.co/datasets/harpomaxx/unix-commands.cqadupstack-unix-fa
Dataset Summary
CQADupstack-unix-Fa is a Persian (Farsi) dataset designed for the Retrieval task, with a focus on duplicate question retrieval. It is a translated version of the "unix" (Unix & Linux Stack Exchange) subforum from the original English CQADupstack dataset, used in the BEIR benchmark, and is part of the FaMTEB (Farsi Massive Text Embedding Benchmark) under the BEIR-Fa collection.
Language(s): Persian (Farsi)
Task(s): Retrieval (Duplicate Question Retrieval)
Source:… See the full description on the dataset page: https://huggingface.co/datasets/MCINext/cqadupstack-unix-fa.cqadupstack-unix-top-20-gen-queries
NFCorpus: 20 generated queries (BEIR Benchmark)
This HF dataset contains the top-20 synthetic queries generated for each passage in the above BEIR benchmark dataset.
DocT5query model used: BeIR/query-gen-msmarco-t5-base-v1
id (str): unique document id in NFCorpus in the BEIR benchmark (corpus.jsonl).
Questions generated: 20
Code used for generation: evaluate_anserini_docT5query_parallel.py
Below contains the old dataset card for the BEIR benchmark.
Dataset Card for BEIR… See the full description on the dataset page: https://huggingface.co/datasets/income/cqadupstack-unix-top-20-gen-queries.social-media-postunixlogfilesshellm-V3-simple-unixunix-dataset-small