41 lines
1.1 KiB
Markdown
41 lines
1.1 KiB
Markdown
---
|
|
license: cc-by-nc-4.0
|
|
tags:
|
|
- not-for-all-audiences
|
|
- nsfw
|
|
---
|
|
|
|
Mixtral-4x7B-DPO-RPChat is a model made primarely for RP (Roleplay), 2 RP model, 1 occult model and 1 DPO model for a MoE. Toppy was the base.
|
|
|
|
The DPO was here to help get more human reply
|
|
|
|
This is my first try at doing this, so don't hesitate to give feedback!
|
|
|
|
WARNING: ALL THE "K" GGUF QUANT OF MIXTRAL MODELS SEEMS TO BE [BROKEN](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/TvjEP14ps7ZUgJ-0-mhIX.png), PREFER Q4_0, Q5_0 or Q8_0!
|
|
|
|
<!-- description start -->
|
|
## Description
|
|
|
|
This repo contains fp16 files of Mixtral-4x7B-DPO-RPChat.
|
|
|
|
<!-- description end -->
|
|
<!-- description start -->
|
|
## Models used
|
|
|
|
The list of model used and their activator/theme can be found [here](https://huggingface.co/Undi95/Mixtral-4x7B-DPO-RPChat/blob/main/config.yaml)
|
|
|
|
<!-- description end -->
|
|
<!-- prompt-template start -->
|
|
## Prompt template: Alpaca
|
|
|
|
```
|
|
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
|
|
|
### Instruction:
|
|
{prompt}
|
|
|
|
### Response:
|
|
```
|
|
|
|
If you want to support me, you can [here](https://ko-fi.com/undiai).
|