Scaling Code Llama Parameters from 7B to 70B on Imbalanced Multilingual Code Security Benchmarks

This report synthesises findings from 12 peer-reviewed papers addressing the following research question: Does increasing parameter count from 7B to 70B mitigate the performance drop caused by imbalanced training data distributions in multi-language code security benchmarks. We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks. We provide. 16 claims were extracted from source literature; 14 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Does increasing parameter count from 7B to 70B mitigate the performance drop caused by imbalanced training data distributions in multi-language code security benchmarks?

Autonomous literature synthesis. Automated review score: 8.2/10. Full text and citation available at Assignee Research.