LLM Model Merging Techniques

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

# SLERP formula
merged = (sin((1-t)*θ) / sin(θ)) * model1 + (sin(t*θ) / sin(θ)) * model2
# where θ = arccos(dot(model1, model2))
# t ∈ [0, 1]

Task Arithmetic

• Extract "task vectors" (fine-tuned - base)
• Combine task vectors, add to base
• Good for merging multiple specialized models (merged = base + α₁·tv₁ + α₂·tv₂)

TIES-Merging

• Task arithmetic + sparsification
• Resolves sign conflicts in parameters
• Best for merging many task-specific models

DARE (Drop And REscale)

• Randomly drops fine-tuned parameters
• Rescales remaining parameters
• Reduces redundancy, maintains performance

2. Configuration Structure

# Basic structure
merge_method: <method>  # linear, slerp, ties, dare_ties, task_arithmetic
base_model: <path>      # Optional: base model for task arithmetic

models:
  - model: <path/to/model1>
    parameters:
      weight: <float>   # Merge weight
      density: <float>  # For TIES/DARE

  - model: <path/to/model2>
    parameters:
      weight: <float>

parameters:
  # Method-specific parameters

dtype: <dtype>  # bfloat16, float16, float32

# Optional
slices:  # Layer-wise merging
tokenizer:  # Tokenizer configuration

Merge Methods Guide

Linear Merge

Best for: Simple model combinations, equal weighting

merge_method: linear
models:
  - model: WizardLM/WizardMath-7B-V1.1
    parameters:
      weight: 0.4
  - model: teknium/OpenHermes-2.5-Mistral-7B
    parameters:
      weight: 0.3
  - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
    parameters:
      weight: 0.3
dtype: bfloat16

SLERP Merge

Best for: Two models, smooth 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  # 0.0 = first model, 1.0 = second model
dtype: bfloat16

Layer-specific SLERP:

merge_method: slerp
slices:
  - sources:
      - model: model_a
        layer_range: [0, 32]
      - model: model_b
        layer_range: [0, 32]
parameters:
  t:
    - filter: self_attn    # Attention layers
      value: 0.3
    - filter: mlp          # MLP layers
      value: 0.7
    - value: 0.5           # Default for other layers
dtype: bfloat16

Task Arithmetic

Best for: Combining specialized skills

merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: WizardLM/WizardMath-7B-V1.1  # Math
    parameters:
      weight: 0.5
  - model: teknium/OpenHermes-2.5-Mistral-7B  # Chat
    parameters:
      weight: 0.3
  - model: ajibawa-2023/Code-Mistral-7B  # Code
    parameters:
      weight: 0.2
dtype: bfloat16

TIES-Merging

Best for: Many models, resolving conflicts

merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: WizardLM/WizardMath-7B-V1.1
    parameters:
      density: 0.5  # Keep top 50% of parameters
      weight: 1.0
  - model: teknium/OpenHermes-2.5-Mistral-7B
    parameters:
      density: 0.5
      weight: 1.0
  - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
    parameters:
      density: 0.5
      weight: 1.0
parameters:
  normalize: true
dtype: bfloat16

DARE Merge

Best for: Reducing redundancy

merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: WizardLM/WizardMath-7B-V1.1
    parameters:
      density: 0.5    # Drop 50% of deltas
      weight: 0.6
  - model: teknium/OpenHermes-2.5-Mistral-7B
    parameters:
      density: 0.5
      weight: 0.4
parameters:
  int8_mask: true  # Use int8 for masks (saves memory)
dtype: bfloat16

Advanced Patterns

Layer-wise Merging

# Different models for different layers
merge_method: passthrough
slices:
  - sources:
      - model: mistralai/Mistral-7B-v0.1
        layer_range: [0, 16]   # First half
  - sources:
      - model: teknium/OpenHermes-2.5-Mistral-7B
        layer_range: [16, 32]  # Second half
dtype: bfloat16

MoE from Merged Models

# Create Mixture of Experts
merge_method: moe
base_model: mistralai/Mistral-7B-v0.1
experts:
  - source_model: WizardLM/WizardMath-7B-V1.1
    positive_prompts:
      - "math"
      - "calculate"
  - source_model: teknium/OpenHermes-2.5-Mistral-7B
    positive_prompts:
      - "chat"
      - "conversation"
  - source_model: ajibawa-2023/Code-Mistral-7B
    positive_prompts:
      - "code"
      - "python"
dtype: bfloat16

Tokenizer Merging

merge_method: linear
models:
  - model: mistralai/Mistral-7B-v0.1
  - model: custom/specialized-model

tokenizer:
  source: "union"  # Combine vocabularies from both models
  tokens:
    <|special_token|>:
      source: "custom/specialized-model"

Best Practices

1. Model Compatibility

# ✅ Good: Same architecture
models = [
    "mistralai/Mistral-7B-v0.1",
    "teknium/OpenHermes-2.5-Mistral-7B",  # Both Mistral 7B
]

# ❌ Bad: Different architectures
models = [
    "meta-llama/Llama-2-7b-hf",  # Llama
    "mistralai/Mistral-7B-v0.1",  # Mistral (incompatible!)
]

2. Weight Selection

# ✅ Good: Weights sum to 1.0
models:
  - model: model_a
    parameters:
      weight: 0.6
  - model: model_b
    parameters:
      weight: 0.4  # 0.6 + 0.4 = 1.0

# ⚠️  Acceptable: Weights don't sum to 1 (for task arithmetic)
models:
  - model: model_a
    parameters:
      weight: 0.8
  - model: model_b
    parameters:
      weight: 0.8  # May boost performance

Unsupervised Coefficient Tuning (no labeled data needed)

Instead of manual search, use generation consistency: merge with several candidate coefficients, generate responses on a small unlabeled subset, and pick the coefficient whose outputs are most similar to those of its neighbors. Consistent outputs signal a stable, well-performing merge region (AdaMMS, arXiv:2503.23733).

# Pseudocode — see references/coefficient-tuning.md for full implementation
candidates = [0.3, 0.4, 0.5, 0.6, 0.7]
for alpha in candidates:
    merged_paths[alpha] = merge_with_coefficient(alpha, model_a, model_b)
    responses[alpha]    = generate_responses(merged_paths[alpha], eval_prompts)

# Score each alpha by similarity to its neighbors (alpha ± 0.1)
best_alpha = max(candidates, key=lambda a: generation_consistency(a, responses))

See references/coefficient-tuning.md for the full algorithm, similarity metrics, multi-coefficient search, and end-to-end pipeline.

3. Method Selection

# Choose merge method based on use case:

# 2 models, smooth blend → SLERP
merge_method = "slerp"

# 3+ models, simple average → Linear
merge_method = "linear"

# Multiple task-specific models → Task Arithmetic or TIES
merge_method = "ties"

# Want to reduce redundancy → DARE
merge_method = "dare_ties"

4. Density Tuning (TIES/DARE)

# Start conservative (keep more parameters)
parameters:
  density: 0.8  # Keep 80%

# If performance good, increase sparsity
parameters:
  density: 0.5  # Keep 50%

# If performance degrades, reduce sparsity
parameters:
  density: 0.9  # Keep 90%

5. Layer-specific Merging

Preserve the base model's first/last layers (often best left untouched) and merge only the middle via merge_method: passthrough with slices — see the Layer-wise Merging pattern above.

Evaluation & Testing

Benchmark Merged Models

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load merged model
model = AutoModelForCausalLM.from_pretrained("./merged-model")
tokenizer = AutoTokenizer.from_pretrained("./merged-model")

# Test on various tasks
test_prompts = {
    "math": "Calculate: 25 * 17 =",
    "code": "Write a Python function to reverse a string:",
    "chat": "What is the capital of France?",
}

for task, prompt in test_prompts.items():
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=100)
    print(f"{task}: {tokenizer.decode(outputs[0])}")

Common Benchmarks

• Open LLM Leaderboard: General capabilities
• MT-Bench: Multi-turn conversation
• MMLU: Multitask accuracy
• HumanEval: Code generation
• GSM8K: Math reasoning

Production Deployment

Save and Upload

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load merged model
model = AutoModelForCausalLM.from_pretrained("./merged-model")
tokenizer = AutoTokenizer.from_pretrained("./merged-model")

# Upload to HuggingFace Hub
model.push_to_hub("username/my-merged-model")
tokenizer.push_to_hub("username/my-merged-model")

Quantize Merged Model

# Quantize with GGUF
python convert.py ./merged-model --outtype f16 --outfile merged-model.gguf

# Quantize with GPTQ
python quantize_gptq.py ./merged-model --bits 4 --group_size 128

Common Pitfalls

• Mismatched architectures — only merge models that share the same architecture (e.g., don't mix Llama and Mistral).
• Over-weighting one model (e.g., 0.95 / 0.05) — keep weights balanced, typically in the 0.3–0.7 range.
• Skipping evaluation — always benchmark a merged model before deploying (see the Evaluation & Testing section above).

Resources

• mergekit GitHub: https://github.com/arcee-ai/mergekit
• HuggingFace Tutorial: https://huggingface.co/blog/mlabonne/merge-models
• LazyMergekit: Automated merging notebook
• TIES Paper: https://arxiv.org/abs/2306.01708
• DARE Paper: https://arxiv.org/abs/2311.03099

See Also

• references/methods.md - Deep dive into merge algorithms
• references/examples.md - Real-world merge configurations
• references/evaluation.md - Benchmarking and testing strategies
• references/coefficient-tuning.md - Unsupervised coefficient search via generation consistency (AdaMMS, arXiv:2503.23733)