datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
srsRANBench
srsRANBench: A Benchmark for Assessing LLMs in srsRAN Code Understanding
Overview
srsRANBench is a comprehensive benchmark dataset designed to evaluate Large Language Models (LLMs) in the context of code generation and code understanding for the srsRAN project. This benchmark consists of 1,502 multiple-choice questions, carefully curated by randomly selecting C++ files from the entire srsRAN codebase.
The benchmark assesses LLMs' ability to generate syntactically and… See the full description on the dataset page: https://huggingface.co/datasets/prnshv/srsRANBench.srsRANBench
srsRANBench: A Benchmark for Assessing LLMs in srsRAN Code Understanding
Overview
srsRANBench is a comprehensive benchmark dataset designed to evaluate Large Language Models (LLMs) in the context of code generation and code understanding for the srsRAN project. This benchmark consists of 1,502 multiple-choice questions, carefully curated by randomly selecting C++ files from the entire srsRAN codebase.
The benchmark assesses LLMs' ability to generate syntactically and… See the full description on the dataset page: https://huggingface.co/datasets/qubol/srsRANBench.