Neural-Dark-Waifu / README.md
nocudaexe's picture
Update README.md
77123d4 verified
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65bcd419d5341c3e56189303/ZVMMNbEbp2Z0MR-DphGtH.png)
[nocudaexe/Neural-Dark-Waifu-GGUF](https://huggingface.co/nocudaexe/Neural-Dark-Waifu-GGUF) GGUF version
Potentially broken
Use: [nocudaexe/Neural-Dark-Waifu-v0.2](https://huggingface.co/nocudaexe/Neural-Dark-Waifu-v0.2) tested to 15872 tokens
---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- nocudaexe/Dark-Waifu-7b
- nocudaexe/Infinite-Waifu
---
# DarkNeural
DarkNeural is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [nocudaexe/Dark-Waifu-7b](https://huggingface.co/nocudaexe/Dark-Waifu-7b)
* [nocudaexe/Infinite-Waifu](https://huggingface.co/nocudaexe/Infinite-Waifu)
## 🧩 Configuration
\```yamlmodels:
- model: Test157t/Kunocchini-7b-128k-test
# No parameters necessary for base model
- model: nocudaexe/Dark-Waifu-7b
parameters:
density: 0.33
weight: 0.4
- model: nocudaexe/Infinite-Waifu
parameters:
density: 0.38
weight: 0.3
merge_method: dare_ties
base_model: Test157t/Kunocchini-7b-128k-test
parameters:
int8_mask: true
dtype: bfloat16
\```