Model Merging
技能 已验证 活跃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.
Combine capabilities from multiple LLMs to create specialized, higher-performing models efficiently and experiment rapidly with model variants.
功能
- Merge multiple fine-tuned models
- Support for SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging
- Configuration examples for various merge methods
- Guidance on production deployment and quantization
- Combine domain-specific expertise without retraining
使用场景
- Creating specialized models by blending domain-specific expertise (math + coding + chat)
- Improving performance beyond single models
- Experimenting rapidly with model variants in minutes
- Reducing training costs by merging instead of retraining
非目标
- Retraining models from scratch
- Training large language models
- Evaluating merged models beyond the provided guidance
- Developing new model merging techniques
Execution
- info:Pinned dependenciesWhile dependencies are listed, specific version pinning or lockfiles are not explicitly detailed in the SKILL.md, relying on standard pip installation.
安装
请先添加 Marketplace
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skills质量评分
已验证类似扩展
Model Merging
98Merge 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.
Chat Format
100Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
Wrap Up Ritual
100End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.
Project Development
100This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.
Context Compression
100This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.