unsloth-orpo

Unsloth-orpo facilitates one-step preference alignment using Odds Ratio Preference Optimization (ORPO). Unlike DPO, which requires a separate reference model, ORPO incorporates a penalty for disfavore

by cuba6112· Repository·other
Run in AgentAreaBrowse All Skills
Also installable via skills CLI
npx skills add cuba6112/skillfactory/skills/unsloth-orpo

Source

Repo:github.com/cuba6112/skillfactory
Path:skills/unsloth-orpo/SKILL.md(main)

Related in other

agent-memory-yamadashy-repomix

Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'not...

by yamadashy
21,427

task-execution-engine

CLI tool for configuring and monitoring Claude Code

by davila7
18,218

qiuzhi

指导Claude按照二哥的风格撰写求职类文章，包括公司薪资爆料、年终奖盘点、求职攻略、offer选择建议等内容。

by itwanger
16,619
unsloth-orpo | AgentArea Skills