model-merging

model-merging is a skill for Claude Code from Orchestra-Research/AI-Research-SKILLs. It costs 73 tokens per session (3,723 once invoked), scanned A, original, MIT.

A guide to combining several fine-tuned language models into one model without training it again. It covers mergekit methods such as SLERP, TIES-Merging, and DARE.

In plain words
What is it for?
Use it to blend skills such as mathematics, coding, and chat, create model variants, and experiment with different model combinations.
Why use it?
It helps combine specialized abilities while avoiding the time and computing cost of another training run.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the emerging-techniques plugin — 6 skills shipped together

Good fit Use it to blend skills such as mathematics, coding, and chat, create model variants, and experiment with different model combinations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orchestra-research/ai-research-skills/model-merging
About the project

AI Research Skills Library is a collection of reusable instructions that guide AI agents through research and machine-learning engineering tasks, from finding ideas and writing papers to training, evaluation, and deployment. It is for configuring agents such as Claude Code, Codex, and Gemini to perform research workflows.

Orchestra-Research/AI-Research-SKILLs · 12,508 stars · on GitHub · orchestra-research.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Orchestra-Research/AI-Research-SKILLs --skill model-merging
Clone the repo
git clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs

Made for: Claude Code.

Or install emerging-techniques, the plugin that ships this one along with the rest of its 6 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for model-merging

README.md
[![agentmods](https://agentmods.dev/badge/skills/orchestra-research/ai-research-skills/model-merging/github.svg)](https://agentmods.dev/skills/orchestra-research/ai-research-skills/model-merging)
Your own site
<a href="https://agentmods.dev/skills/orchestra-research/ai-research-skills/model-merging"><img src="https://agentmods.dev/badge/skills/orchestra-research/ai-research-skills/model-merging/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for model-merging

Your own site · 80×15
<a href="https://agentmods.dev/skills/orchestra-research/ai-research-skills/model-merging"><img src="https://agentmods.dev/badge/skills/orchestra-research/ai-research-skills/model-merging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,723 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk warn 16 Feb 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.03723
Opus 5 $0.00036 $0.01861
Sonnet 5 $0.00015 $0.00745
Haiku 4.5 $0.00007 $0.00372

Measured 8d ago against content hash dfbcc6d6dfef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

model-merging scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

19-emerging-techniques/model-merging/SKILL.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Merging: Combining Pre-trained Models

When to Use This Skill

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

Installation

# Install mergekit
git clone https://github.com/arcee-ai/mergekit.git
cd mergekit
pip install -e .

# Or via pip
pip install mergekit

# Optional: Transformer library
pip install transformers torch

Quick Start

Simple Linear Merge

# config.yml - Merge two models with equal weights
merge_method: linear
models:
  - model: mistralai/Mistral-7B-v0.1
    parameters:
      weight: 0.5
  - model: teknium/OpenHermes-2.5-Mistral-7B
    parameters:
      weight: 0.5
dtype: bfloat16
# Run merge
mergekit-yaml config.yml ./merged-model --cuda

# Use merged model
python -m transformers.models.auto --model_name_or_path ./merged-model

SLERP Merge (Best for 2 Models)

# config.yml - Spherical interpolation
merge_method: slerp
slices:
  - sources:
      - model: mistralai/Mistral-7B-v0.1
        layer_range: [0, 32]
      - model: teknium/OpenHermes-2.5-Mistral-7B
        layer_range: [0, 32]
parameters:
  t: 0.5  # Interpolation factor (0=model1, 1=model2)
dtype: bfloat16

Core Concepts

1. Merge Methods

Linear (Model Soup)

  • Simple weighted average of parameters
  • Fast, works well for similar models
  • Can merge 2+ models (w1 + w2 + ... = 1)

SLERP (Spherical Linear Interpolation)

  • Interpolates along sphere in weight space
  • Preserves magnitude of weight vectors
  • Best for merging 2 models
  • Smoother than linear

Read the full file on GitHub · 498 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 498 lines · 73 tokens per session scan A dfbcc6d6dfef

Subscribe to this mod's changes

model-merging is a skill published in the GitHub repository Orchestra-Research/AI-Research-SKILLs (12,508 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 3,723 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

model-merging

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…

davila7/claude-code-templates · 73 tokens

model-merging

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…

OpenLAIR/dr-claw · 73 tokens

model-merging

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…

liortesta/ClawdAgent · 73 tokens

model-merging

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…

OpenLAIR/dr-claw-plugin-cc · 73 tokens

model-merging

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…

ihatesea69/HieuNghi-AI-Skills · 73 tokens

knowledge-distillation

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and…

davila7/claude-code-templates · 65 tokens