00:00:00

Share Your Feedback 🏝️

Every Sample Matters

Every Sample Matters

MinWoo(Daniel) Park | Tech Blog

Read more
Previous: I Have Covered All the Bases Next: Understanding R1-Zero-Like Training

Every Sample Matters

  • Related Project: Private
  • Category: Paper Review
  • Date: 2025-03-26

Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM

  • url: https://arxiv.org/abs/2503.17793
  • pdf: https://arxiv.org/pdf/2503.17793
  • html: https://arxiv.org/html/2503.17793v1
  • abstract: Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency. Many attempts have been released in the open source community to break the trade-off between performance and efficiency, such as the Qwen Coder series and the DeepSeek Coder series. This paper introduces yet another attempt in this area, namely Ling-Coder-Lite. We leverage the efficient Mixture-of-Experts (MoE) architecture along with a set of high-quality data curation methods (especially those based on program analytics) to build an efficient yet powerful code LLM. Ling-Coder-Lite exhibits on-par performance on 12 representative coding benchmarks compared to state-of-the-art models of similar size, such as Qwen2.5-Coder-7B and DeepSeek-Coder-V2-Lite, while offering competitive latency and throughput. In practice, we achieve a 50\% reduction in deployment resources compared to the similar-sized dense model without performance loss. To facilitate further research and development in this area, we open-source our models as well as a substantial portion of high-quality data for the annealing and post-training stages. The models and data can be accessed at~\url{this https URL}.
Previous: I Have Covered All the Bases Next: Understanding R1-Zero-Like Training

post contain ""

    No matching posts found containing ""