aiXcoder-7B-v2: Training LLMs to Fully Utilize the Long Context in Repository-level Code Completion

Documenti analoghi

• aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Processing
  di: Jiang, Siyuan, et al.
  Pubblicazione: (2024)
• CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
  di: Zhang, Kechi, et al.
  Pubblicazione: (2024)
• Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points
  di: Zhang, Kechi, et al.
  Pubblicazione: (2025)
• LONGCODEU: Benchmarking Long-Context Language Models on Long Code Understanding
  di: Li, Jia, et al.
  Pubblicazione: (2025)
• EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories
  di: Li, Jia, et al.
  Pubblicazione: (2024)