AIbase
Product LibraryTool Navigation

DeepSeek-671B-SFT-Guide

Public

An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案,包含从训练到推理的完整代码和脚本,以及实践中积累一些经验和结论。)

Creat2025-03-07T14:22:01
Update2025-03-27T12:41:59
582
Stars
3
Stars Increase

Related projects