基于大模型的应用开源问题:Open Issues in LLM-based Applications
大语言模型作为一股技术变革力量正在快速重塑我们与信息世界的交互方式。随着大语言模型能力的增长,其研发过程中涉及到数据、训练、部署、价值对齐等方面的深层次技术问题逐步凸显出来。在此背景下,我们总结了与大模型相关的7个技术问题,并希望通过开源协作的方式来推动问题的持续深入研究。
基于大模型的应用开源问题:Open Issues in LLM-based Applications
大模型训练过程版本演化分析及工具开源问题:Open Issues in Analysis and Tools for the Evolution of LLM Version in Training Process
大模型数学推理相关开源问题:Open Issues in LLM-based Mathematical Reasoning
大模型运行时监控开源问题:Open Issues in the Runtime Monitoring for LLM
基于国产算力的大模型推理优化开源问题:Open Issues in the Optimization of LLM Inference based on Domestic Computing Power
基于人类反馈的模型调优方法开源问题:Open Issues in the LLM Fine-tuning based on Human Feedback
数据质量度量及缺陷检测技术开源问题:Open Issues in Data Quality Metrics and Defect Detection
基于大模型的智能应用开发环境开源问题:Open Issues in the Development Environment of LLM based Intelligent Applications
大模型全周期开源问题:Open issues in LLM life circle
Select up to 9 public projects
基于大模型的应用开源问题:Open Issues in LLM-based Applications
Updated 3 months ago
大模型训练过程版本演化分析及工具开源问题:Open Issues in Analysis and Tools for the Evolution of LLM Version in Training Process
Updated 5 months ago
大模型数学推理相关开源问题:Open Issues in LLM-based Mathematical Reasoning
Updated 6 months ago
大模型运行时监控开源问题:Open Issues in the Runtime Monitoring for LLM
Updated 6 months ago
基于国产算力的大模型推理优化开源问题:Open Issues in the Optimization of LLM Inference based on Domestic Computing Power
Updated 6 months ago
基于人类反馈的模型调优方法开源问题:Open Issues in the LLM Fine-tuning based on Human Feedback
Updated 6 months ago
数据质量度量及缺陷检测技术开源问题:Open Issues in Data Quality Metrics and Defect Detection
Updated 6 months ago
基于大模型的智能应用开发环境开源问题:Open Issues in the Development Environment of LLM based Intelligent Applications
Updated 6 months ago
大模型全周期开源问题:Open issues in LLM life circle
Updated 6 months ago
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》