emerging-techniques-model-merging

原文涵盖的主题

• Model Merging: Combining Pre-trained Models
• When to Use This Skill
• Installation
• Quick Start
• Simple Linear Merge
• SLERP Merge (Best for 2 Models)
• Core Concepts
• 1. Merge Methods

Use Model Merging when you need to: Combine capabilities from multiple fine-tuned models without retraining Create specialized models by blending domain-specific expertise (math + coding + chat) Improve performance beyond single models (often +5-10% on benchmarks) Reduce training costs - no GPUs needed, merges run on CPU Experiment rapidly - create new model variants in minutes, not days Preserve multiple skills - merge without catastrophic forgetting Success Stories: Marcoro14-7B-slerp (best on Open LLM Leaderboard 02/2024), many top HuggingFace models use merging Tools: mergekit (Arcee AI), LazyMergekit, Model Soup Linear (Model Soup) Simple weighted average of parameters Fast, works well for similar models Can merge 2+ models SLERP (Spherical Linear Interpolation) Interpolates along sphere in weight space Preserves magnitude of weight vectors Best for merging 2 models Smoother than linear Task Arithmetic Extract "task vectors" (fine-tuned - base) Combine task vectors, add to base Good for merging multiple specialized models TIES-Merging Task arithmetic + sparsification Resolves sign conflicts in parameters Best for merging many task-specific models DARE (Drop And REscale) Random

这里只展示节选，请以完整原文和当前要求为准。