Model Merging

orchestra-research/ai-research-skills/19-emerging-techniques/model-merging

作者 orchestra-research773a52944ba4MIT13K 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫3 個月前更新

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

僅含說明AI & Agents

僅公開檔案列表。將技能安裝到工作區後即可檢視檔案內容。

路徑大小類型
references/coefficient-tuning.md14.3 KBtext/markdown
references/evaluation.md11.4 KBtext/markdown
references/examples.md8.6 KBtext/markdown
references/methods.md9.3 KBtext/markdown
SKILL.md12.5 KBtext/markdown

來源與署名

來源:orchestra-research/ai-research-skills位於19-emerging-techniques/model-merging提交773a529

授權條款: MIT

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架