datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
llm-evaluation-sft-100k
LLM Evaluation SFT 100K
A synthetic supervised fine-tuning dataset of 100,000 high-quality conversations covering LLM evaluation methodology, benchmarking, safety assessment, and prompt optimization. Designed to train AI assistants that can help ML engineers and researchers rigorously evaluate and improve language models.
Dataset Description
This dataset covers the full spectrum of LLM evaluation practice across 7 specialized categories. Each record follows the… See the full description on the dataset page: https://huggingface.co/datasets/stindardlogic/llm-evaluation-sft-100k.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.