Dataset - LDM

ExtractFix Dataset

This dataset contains 12 real-world vulnerabilities across three projects.
- Dataset
- JSON
HumanEvalFix

HumanEvalFix is a benchmark for evaluating the performance of code repair models.
- Dataset
- JSON
Code Comparison Tuning

Code Comparison Tuning (CCT) is a simple and effective tuning method for code large language models (Code LLMs) to better handle subtle code errors.
- Dataset
- JSON

You can also access this registry using the API (see API Docs).

3 datasets found