datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
multilingual-llm-evaluation
Multilingual LLM Evaluation
A small evaluation dataset for comparing language models across English, Hindi, and Spanish.
Columns
language: language code (en, hi, or es)
question: question provided to the model
expected_answer: reference answer used for scoring
Intended use
This dataset can be used to compare model accuracy, language adherence, and response speed across languages.
Limitations
This is a small demonstration dataset and… See the full description on the dataset page: https://huggingface.co/datasets/userhuggingface4321/multilingual-llm-evaluation.User-Documentation-QA
Keboola QA Pairs
Dataset SummaryA concise set of Q&A pairs derived from Keboola user documentation, each question and answer is self-contained and domain-specific. Suitable for training or evaluation of QA and retrieval-augmented generation models.
Metadata
Dataset Name: keboola-qa-pairs
Language: English (en)
Task Categories: Question-Answering, Retrieval-Augmented Generation
Size: ~3000
Source: Keboola documentation excerpts
Sample Data
{
"question": "How… See the full description on the dataset page: https://huggingface.co/datasets/Keboola/User-Documentation-QA.