|
--- |
|
library_name: transformers |
|
tags: |
|
- unsloth |
|
license: llama3 |
|
datasets: |
|
- unalignment/toxic-dpo-v0.2 |
|
- NobodyExistsOnTheInternet/ToxicQAFinal |
|
- Open-Orca/SlimOrca |
|
- PygmalionAI/PIPPA |
|
- MinervaAI/Aesir-Preview |
|
language: |
|
- en |
|
--- |
|
|
|
 |
|
|
|
# Disclaimer |
|
|
|
This model is an experimental fine tune of LLama-3 |
|
|
|
## Datasets used: |
|
|
|
- unalignment/toxic-dpo-v0.2 |
|
- NobodyExistsOnTheInternet/ToxicQAFinal |
|
- Open-Orca/SlimOrca (subset of data) |
|
- PygmalionAI/PIPPA |
|
- MinervaAI/Aesir-Preview |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
The model is highly uncensored + suitable for roleplay |
|
|
|
## About Us |
|
Building - AI Waifu Supremacy |
|
|
|
[X](https://twitter.com/hikikomorihaven) |
|
|
|
[Discord](discord.gg/QS27Ka3cnq) |
|
|
|
## Credits: |
|
(For open sourcing tools + methodology to assist with fine tuning) |
|
- Unisloth |
|
- NurtureAI |
|
(For open sourcing data to be used for fine tuning) |
|
- NobodyExistsOnTheInternet |
|
- unalignment |
|
- Open-Orca |
|
- PygmalionAI |
|
- MinervaAI |
