---
base_model:
- Qwen/Qwen3-30B-A3B-Base
- Qwen/Qwen3-30B-A3B
license: apache-2.0
library_name: transformers
tags:
- mergekit
- merge

---
# CavesOfQwen3

> Hey Hey, Model Gang, KaraWitch Here.  
> Have you, ever merged too deeply.  
> And found something 'they' don't want you to know?  
> "[CavesOfQwen3](https://youtu.be/o_PBfLbd3zw)", who is she? And why can't I reach her?

![image/png](https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/0z0yzAGcnw36qJ51eDl4Z.png)

CavesOfQwen3 is a merge between the base model and the instruct model of Qwen3-30B-A3B (i.e. Qwen3-30B-A3B) and it's base model Qwen3-30B-A3B-base.

The idea for this merge is to remove the overbaked feeling that is in the instruct while retaining the instruct within the model.  
I've tested the model and it seems to performs reasonably well\*

\*(Ignoring the fact that it's spewing something random at the end. I suspect that's on my part in the configuration of the model on vllm or SillyTavern.)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/n5mf5PA_GSHPX7GgfOW17.png)

This is a merge of pre-trained language models created using ~~mergekit.~~  
This model is done with mergekitty. With a couple of code patch to add qwen3 and a `o_proj` into Qwen3 arch configuration (else vllm get's very grumpy over it.)  
This was me when I found out it didn't have `o_proj`.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/l2fRw1N99wJCVy9v9qwoZ.png)

Thankfully merging can be done on CPU. But not inference!  

I used `TIES`. Not because I'm lazy but because it's what I had lying around that isn't `SCE` or something else.

## Merge Details
### Merge Method

This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen3-30B-A3B](https://huggingface.co/Qwen/Qwen3-30B-A3B) as a base.

### Models Merged

The following models were included in the merge:
* [Qwen/Qwen3-30B-A3B-Base](https://huggingface.co/Qwen/Qwen3-30B-A3B-Base)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Qwen/Qwen3-30B-A3B
    parameters:
      density: 0.4
      weight: 0.35
  - model: Qwen/Qwen3-30B-A3B-Base
    parameters:
      density: 0.7
      weight: 1

merge_method: ties
base_model: Qwen/Qwen3-30B-A3B
parameters:
  normalize: true
dtype: bfloat16
```

### Disclaimer.

> CavesOfQwen3 and it's creator is not affiliated with Caves Of Qud or the creator of the video linked.  
> The reference is intentional, but it is supposed to be taken as a light hearted joke.
> There's not need to take it too deeply other than "Haha, funni name."
> This disclaimer is for those who think otherwise or are overthinkers.