OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913746721439744 |
|---|---|
| author | Huang, Siming Cheng, Tianhao Liu, J. K. Hao, Jiaran Song, Liuyihan Xu, Yang Yang, J. Liu, Jiaheng Zhang, Chenchen Chai, Linzheng Yuan, Ruifeng Zhang, Zhaoxiang Fu, Jie Liu, Qian Zhang, Ge Wang, Zili Qi, Yuan Xu, Yinghui Chu, Wei |
| author_facet | Huang, Siming Cheng, Tianhao Liu, J. K. Hao, Jiaran Song, Liuyihan Xu, Yang Yang, J. Liu, Jiaheng Zhang, Chenchen Chai, Linzheng Yuan, Ruifeng Zhang, Zhaoxiang Fu, Jie Liu, Qian Zhang, Ge Wang, Zili Qi, Yuan Xu, Yinghui Chu, Wei |
| contents | Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems. While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs suitable for rigorous scientific investigation, particularly those with reproducible data processing pipelines and transparent training protocols, remain limited. The scarcity is due to various challenges, including resource constraints, ethical considerations, and the competitive advantages of keeping models advanced. To address the gap, we introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community. Unlike most prior efforts, we release not only model weights and inference code, but also the reproducible training data, complete data processing pipeline, rigorous experimental ablation results, and detailed training protocols for open scientific research. Through this comprehensive release, we identify the key ingredients for building a top-tier code LLM: (1) code optimized heuristic rules for data cleaning and methods for data deduplication, (2) recall of text corpus related to code and (3) high-quality synthetic data in both annealing and supervised fine-tuning stages. By offering this level of openness, we aim to broaden access to all aspects of a top-tier code LLM, with OpenCoder serving as both a powerful model and an open foundation to accelerate research, and enable reproducible advancements in code AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04905 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models Huang, Siming Cheng, Tianhao Liu, J. K. Hao, Jiaran Song, Liuyihan Xu, Yang Yang, J. Liu, Jiaheng Zhang, Chenchen Chai, Linzheng Yuan, Ruifeng Zhang, Zhaoxiang Fu, Jie Liu, Qian Zhang, Ge Wang, Zili Qi, Yuan Xu, Yinghui Chu, Wei Computation and Language Programming Languages Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems. While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs suitable for rigorous scientific investigation, particularly those with reproducible data processing pipelines and transparent training protocols, remain limited. The scarcity is due to various challenges, including resource constraints, ethical considerations, and the competitive advantages of keeping models advanced. To address the gap, we introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community. Unlike most prior efforts, we release not only model weights and inference code, but also the reproducible training data, complete data processing pipeline, rigorous experimental ablation results, and detailed training protocols for open scientific research. Through this comprehensive release, we identify the key ingredients for building a top-tier code LLM: (1) code optimized heuristic rules for data cleaning and methods for data deduplication, (2) recall of text corpus related to code and (3) high-quality synthetic data in both annealing and supervised fine-tuning stages. By offering this level of openness, we aim to broaden access to all aspects of a top-tier code LLM, with OpenCoder serving as both a powerful model and an open foundation to accelerate research, and enable reproducible advancements in code AI. |
| title | OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models |
| topic | Computation and Language Programming Languages |
| url | https://arxiv.org/abs/2411.04905 |