dsh-mlops
ML 管线工作流:数据→训练→评估→部署→监控的 MLOps 工程。受 wshobson/agents(38k★ MIT)启发。
34 results
ML 管线工作流:数据→训练→评估→部署→监控的 MLOps 工程。受 wshobson/agents(38k★ MIT)启发。
A small DeepSeek Harness tool plugin for learning the Cordis extension model
DeepSeek Harness plugin for progressive, source-grounded deep research, writing, and learning: steerable checkpoints and citations verified against retrieved sources
把技能当可训练参数:像训练神经网络一样训练 agent 技能(epochs/batchsize/learning rate/验证门禁,但不碰模型权重)——rollout→reflect→aggregate→select→update→evaluate 循环、候选编辑仅在严格改善 held-out 验证分时接受、文本学习率预算、零推理时模型调用、部署紧凑 best_skill.md。受 microsoft/SkillOpt(MIT)启发。
Practice bundle for learning DeepSeek Harness plugin development
Cross-session self-learning memory for DeepSeek Harness, ported from XT-AGENT packages/memory. BM25 relevance injection + background extraction (sanitize/dedupe/merge) + lifecycle archive + memory_read/memory_search/memory_write tools.
Search arXiv for ML/DL/RL papers and check claims against real abstracts.
Turn any markdown, local folder, or GitHub learning repo into a guided course inside DeepSeek Harness: gated skill-tree progression, BKT mastery tracking, SM-2 spaced repetition.
A proof-carrying correction loop for DSH: explicit adoption, scoped recall, and reconstructable delivery.
Local-first Skill load evidence, learning cards, and iteration preparation for DeepSeek Harness