Skip to main content
Search

Foothills Medical Centre

1 related articles

Subscribe to updates
  1. MergeRepair merges multiple code-task adapters and lifts automated program repair by 2.38% pass@1 and 4.01% pass@10 on StarCoder2 without extra training

    The study introduces MergeRepair, which trains one LoRA adapter per task on the Python split of CommitPackFT (59,113 samples, with Bug Fixes/APR at 19.02%) for Development, Bug Fixes, Misc, Test & QA, and Improvement, merges them with weight-averaging, ties, and dare-ties under equal weights, and proposes continual merging that adds adapters sequentially; evaluated on StarCoder2 and Granite 3B code models with HumanEvalFix pass@1/pass@10, it finds that merging task-specific adapters can improve APR without additional training, reaching up to 2.38% pass@1 and 4.

You’re all caught up