Summary
【DNN调参】当用户说"DNN调参"、"深度学习调参"、"调整网络结构"、"调整dropout"、"DNN过拟合"时使用。基于 Optuna TPE 贝叶斯优化,搜索网络架构(层数、宽度、dropout)和训练参数(learning_rate、weight_decay、batch_size),诊断驱动约束搜索空间。前置…
aliyun/qwen-dianjin
npx skills add https://github.com/aliyun/qwen-dianjin
【DNN调参】当用户说"DNN调参"、"深度学习调参"、"调整网络结构"、"调整dropout"、"DNN过拟合"时使用。基于 Optuna TPE 贝叶斯优化,搜索网络架构(层数、宽度、dropout)和训练参数(learning_rate、weight_decay、batch_size),诊断驱动约束搜索空间。前置…
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Top-level workflow skill for USD performance diagnosis and optimization. Handles slow loading, …
2.1K installsTechniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP inp…
1.8K installsUse when adding, modifying, optimizing, or debugging CuTile autotuning code.
1.5K installsOptimize vector index performance for latency, recall, and memory. Use when tuning HNSW paramet…
9.4K installsAgent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using …
6K installsManages GenAI tuning jobs in Agent Platform. Use this to list, get, or cancel ongoing model tun…
6K installsOther skills from aliyun/qwen-dianjin · top by installs.
npx skills add https://github.com/aliyun/qwen-dianjin
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
master