mergekit-gui

The fastest way to perform a model merge 🔥

Specify a YAML configuration file (see examples below) and a HF token and this app will perform the merge and upload the merged model to your user profile. Uses Zero GPU quota to perform the merge.

Next Restart: 2026-09-24 13:35:07 (UTC)

Upload the model as private. If not checked, will be public. Must provide a token.
Examples

Merge Configuration

Mergekit configurations are YAML documents specifying the operations to perform in order to produce your merged model. Below are the primary elements of a configuration file:

  • merge_method: Specifies the method to use for merging models. See Merge Methods for a list.
  • slices: Defines slices of layers from different models to be used. This field is mutually exclusive with models.
  • models: Defines entire models to be used for merging. This field is mutually exclusive with slices.
  • base_model: Specifies the base model used in some merging methods.
  • parameters: Holds various parameters such as weights and densities, which can also be specified at different levels of the configuration.
  • dtype: Specifies the data type used for the merging operation.
  • tokenizer_source: Determines how to construct a tokenizer for the merged model.

Merge Methods

A quick overview of the currently supported merge methods:

Method merge_method value Multi-Model Uses base model
Linear (Model Soups) linear ✅ ❌
SLERP slerp ❌ ✅
Task Arithmetic task_arithmetic ✅ ✅
TIES ties ✅ ✅
DARE TIES dare_ties ✅ ✅
DARE Task Arithmetic dare_linear ✅ ✅
Passthrough passthrough ❌ ❌
Model Stock model_stock ✅ ✅

Citation

This GUI is powered by Arcee's MergeKit. If you use it in your research, please cite the following paper:

@article{goddard2024arcee,
  title={Arcee's MergeKit: A Toolkit for Merging Large Language Models},
  author={Goddard, Charles and Siriwardhana, Shamane and Ehghaghi, Malikeh and Meyers, Luke and Karpukhin, Vlad and Benedict, Brian and McQuade, Mark and Solawetz, Jacob},
  journal={arXiv preprint arXiv:2403.13257},
  year={2024}
}

This Space is heavily inspired by LazyMergeKit by Maxime Labonne (see Colab).