RP-king-12b / README.md
kainatq's picture
Upload folder using huggingface_hub
3e3c91d verified
|
raw
history blame
1.71 kB
---
library_name: transformers
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
base_model:
- MarinaraSpaghetti/NemoMix-Unleashed-12B
- inflatebot/MN-12B-Mag-Mell-R1
- elinas/Chronos-Gold-12B-1.0
- Retreatcost/KansenSakura-Eclipse-RP-12b
- redrix/patricide-12B-Unslop-Mell-v2
---
# RP-king-12b
RP-king-12b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [MarinaraSpaghetti/NemoMix-Unleashed-12B](https://huggingface.co/MarinaraSpaghetti/NemoMix-Unleashed-12B)
* [inflatebot/MN-12B-Mag-Mell-R1](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1)
* [elinas/Chronos-Gold-12B-1.0](https://huggingface.co/elinas/Chronos-Gold-12B-1.0)
* [Retreatcost/KansenSakura-Eclipse-RP-12b](https://huggingface.co/Retreatcost/KansenSakura-Eclipse-RP-12b)
* [redrix/patricide-12B-Unslop-Mell-v2](https://huggingface.co/redrix/patricide-12B-Unslop-Mell-v2)
## 🧩 Configuration
```yamlmodels:
- model: MarinaraSpaghetti/NemoMix-Unleashed-12B # Base model for creative foundation
parameters:
density: 0.65
weight: 1.0
- model: inflatebot/MN-12B-Mag-Mell-R1 # For worldbuilding and prose
parameters:
density: 0.8
weight: 1.2
- model: elinas/Chronos-Gold-12B-1.0 # For roleplay and prompt adherence
parameters:
density: 0.9
weight: 1.1
- model: Retreatcost/KansenSakura-Eclipse-RP-12b
parameters:
density: 0.5
weight: 0.7
- model: redrix/patricide-12B-Unslop-Mell-v2 # For anti-GPTism and balance
parameters:
density: 0.6
weight: 0.9
merge_method: dare_ties
base_model: MarinaraSpaghetti/NemoMix-Unleashed-12B
parameters:
normalize: true
dtype: bfloat16
tokenizer_source: base```