# Trouble with mergekit

**URL:** <https://discuss.huggingface.co/t/trouble-with-mergekit/99135>\
**Category:** Models\
**Created:** [July 24, 2024, 10:56am UTC](https://discuss.huggingface.co/t/trouble-with-mergekit/99135 "2024-07-24T10:56:09Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![SzilviaB](https://avatars.discourse-cdn.com/v4/letter/s/f17d59/32.png) [@SzilviaB](https://discuss.huggingface.co/u/SzilviaB)\
**Post date:** [July 24, 2024, 10:56am UTC](https://discuss.huggingface.co/t/trouble-with-mergekit/99135/1 "2024-07-24T10:56:09Z")

</div>

I tried using the mergekit.

I used this provided yaml file as a template, just changed the model names.

models:

- model: mistralai/Mistral-7B-v0.1  
#no parameters necessary for base model
- model: mistralai/Mistral-7B-Instruct-v0.2  
parameters:  
density: 0.5  
weight: 0.5
- model: BioMistral/BioMistral-7B  
parameters:  
density: 0.5  
weight: 0.5

merge\_method: ties  
base\_model: mistralai/Mistral-7B-v0.1  
parameters:  
normalize: false  
int8\_mask: true  
dtype: float16

It did not work and just said “error”.

I did leave this field empty:

HF Write Token

> **[Hugging Face – The AI community building the future.](https://huggingface.co/login?next=%2Fsettings%2Ftoken)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

How do tokens work, do you need one to use the mergekit ?

Was the error because of the token or something else ?

Can you make a model straight to GGUF instead of float 16 ?
