Feb. 23, 2024, 5:48 a.m. | Tianyu Zheng, Ge Zhang, Tianhao Shen, Xueling Liu, Bill Yuchen Lin, Jie Fu, Wenhu Chen, Xiang Yue

cs.CL updates on arXiv.org arxiv.org

arXiv:2402.14658v1 Announce Type: cross
Abstract: The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter. To address this, we introduce OpenCodeInterpreter, a family of open-source code systems designed for generating, executing, and iteratively refining code. Supported by Code-Feedback, a dataset featuring 68K multi-turn interactions, OpenCodeInterpreter integrates execution and human feedback for dynamic code refinement. Our comprehensive evaluation of OpenCodeInterpreter across …

abstract advanced arxiv capabilities code code generation cs.ai cs.cl cs.se family gpt gpt-4 interpreter introduction iterative language language models large language large language models open-source models systems type

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US