How to use from
Unsloth StudioInstall Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for hikikomoriHaven/llama3-8b-hikikomori-v0.4 to start chattingUsing HuggingFace Spaces for Unsloth
# No setup required# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hikikomoriHaven/llama3-8b-hikikomori-v0.4 to start chattingLoad model with FastModel
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="hikikomoriHaven/llama3-8b-hikikomori-v0.4",
max_seq_length=2048,
)Quick Links
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
The model is highly uncensored + suitable for roleplay
About Us
Building - AI Waifu Supremacy
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
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install Unsloth Studio (macOS, Linux, WSL)
# Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for hikikomoriHaven/llama3-8b-hikikomori-v0.4 to start chatting