Recently.IDEA InstituteThe team of sealers joins theAIlarge modelthe open source trend, has released its latest code big model, Ziya-Coding-34B-v1.0. This model has achieved excellent results on the HumanEval Pass@1, achieving a score of 75.5, surpassing the GPT-4.
Ziya-Coding-34B-v1.0 is built based on the pre-trained model of Code LLaMA34B, and after two phases of supervised fine-tuning, it is equipped with support for a wide range of code-related tasks, including code generation, code interpretation, code error correction, and unit test generation, among others.
If you are interested in this program, you can find more information at the following address:
- ModelScope Address:https://modelscope.cn/models/Fengshenbang/Ziya-Coding-34B-v1.0
- Huggingface address:https://huggingface.co/IDEA-CCNL/Ziya-Coding-34B-v1.0
The open source of Ziya-Coding-34B-v1.0 provides an important resource for the development of code generation and related fields, and also demonstrates the excellent ability of the Seal Team in the research of large models, which lays a solid foundation for future technological innovations and applications.
This article comes from users or anonymous contributions, does not represent the position of Mass Intelligence; all content (including images, videos, etc.) in this article are copyrighted by the original author. Please refer to this site for the relevant issues involvedstatement denying or limiting responsibilityPlease contact the operator of this website for any infringement of rights (Contact Us) We will handle this as stated. Link to this article: https://dzzn.com/en/2023/1557.html
