---
base_model:
- ReadyArt/The-Omega-Directive-Qwen3-14B-v1.1
- nbeerbower/Vitus-Qwen3-14B
library_name: transformers
tags:
- mergekit
- merge
- roleplay
- co-writing
license: cc-by-nc-4.0
language:
- en
- ja
- zh
- vi
- ru
---
# What is this?

Qwen 3 14B merge, test with some languages and the result is good for this model styles. English and Chinese is the main languages that perform best, following by Japanese and Vietnamese and Russia. Other languages haven't tested.

Good for co-writing btw, roleplay is also good but it's talk for user several times. 


## ChatML is the template. You should add ``/no_think`` or any method to disable thinking process for best result in writing. 

### Configuration

The following YAML configuration was used to produce this model:

```yaml

models:
  - model: nbeerbower/Vitus-Qwen3-14B
    parameters:
      density: 0.9
      weight: 1
  - model: ReadyArt/The-Omega-Directive-Qwen3-14B-v1.1
    parameters:
      density: 0.8
      weight: 0.8
merge_method: dare_ties
base_model: nbeerbower/Vitus-Qwen3-14B
parameters:
  normalize: true
  rescale: true
tokenizer_source: nbeerbower/Vitus-Qwen3-14B
dtype: bfloat16

```