---
base_model:
- Delta-Vector/Hamanasu-QwQ-V1.5-Instruct
- allura-org/Qwen2.5-32b-RP-Ink
- Delta-Vector/Hamanasu-Magnum-QwQ-32B
- THU-KEG/LongWriter-Zero-32B
- zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
- rombodawg/Rombos-LLM-V2.5-Qwen-32b
library_name: transformers
tags:
- mergekit
- merge
- qwen2
- qwq
- creative writing
- storytelling
- roleplay
- non-thinking
---
# Phr00tyMix-v1-32B
Note: this model has been superseded by [Phr00tyMix-v2](https://huggingface.co/Phr00t/Phr00tyMix-v2-32B)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/631be8402ea8535ea48abbc6/qPjrxIblNAdqDxhTQ5uAG.png)

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

The goal is to be smart, obedient, creative and coherent. This isn't 100% censored, but some simple prompting to disallow refusals seems to do the trick.

GGUFs can be [found here](https://huggingface.co/Phr00t/Phr00tyMix-v1-32B-GGUF)

## Merge Details
### Merge Method

This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [rombodawg/Rombos-LLM-V2.5-Qwen-32b](https://huggingface.co/rombodawg/Rombos-LLM-V2.5-Qwen-32b) as a base.

This base model was chosen as a smart, non-thinking foundation.

### Models Merged

The following models were included in the merge:
* [Delta-Vector/Hamanasu-QwQ-V1.5-Instruct](https://huggingface.co/Delta-Vector/Hamanasu-QwQ-V1.5-Instruct) (non-thinking QwQ instruction finetune)
* [allura-org/Qwen2.5-32b-RP-Ink](https://huggingface.co/allura-org/Qwen2.5-32b-RP-Ink) (spicy color and prose)
* [Delta-Vector/Hamanasu-Magnum-QwQ-32B](https://huggingface.co/Delta-Vector/Hamanasu-Magnum-QwQ-32B) (non-thinking QwQ creative finetune)
* [THU-KEG/LongWriter-Zero-32B](https://huggingface.co/THU-KEG/LongWriter-Zero-32B) (coherency for longer writing)
* [zetasepic/Qwen2.5-32B-Instruct-abliterated-v2](https://huggingface.co/zetasepic/Qwen2.5-32B-Instruct-abliterated-v2) (reduced refusals)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: dare_ties
dtype: bfloat16
base_model: rombodawg/Rombos-LLM-V2.5-Qwen-32b
parameters:
  normalize_weights: true
models:
  - model: Delta-Vector/Hamanasu-QwQ-V1.5-Instruct
    parameters:
      weight: 0.3
      density: 1
  - model: zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
    parameters:
      weight: 0.1
      density: 0.8
  - model: THU-KEG/LongWriter-Zero-32B
    parameters:
      weight: 0.1
      density: 0.8
  - model: Delta-Vector/Hamanasu-Magnum-QwQ-32B
    parameters:
      weight: 0.3
      density: 0.8
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight: 0.2
      density: 0.5
```