Instructions to use ringusTheImp/darkScribe-daredevil-8B-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ringusTheImp/darkScribe-daredevil-8B-abliterated with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ringusTheImp/darkScribe-daredevil-8B-abliterated",
	filename="darkScribe-daredevil-8B-abliterated.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ringusTheImp/darkScribe-daredevil-8B-abliterated with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ringusTheImp/darkScribe-daredevil-8B-abliterated
# Run inference directly in the terminal:
llama-cli -hf ringusTheImp/darkScribe-daredevil-8B-abliterated

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ringusTheImp/darkScribe-daredevil-8B-abliterated
# Run inference directly in the terminal:
llama-cli -hf ringusTheImp/darkScribe-daredevil-8B-abliterated

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ringusTheImp/darkScribe-daredevil-8B-abliterated
# Run inference directly in the terminal:
./llama-cli -hf ringusTheImp/darkScribe-daredevil-8B-abliterated

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ringusTheImp/darkScribe-daredevil-8B-abliterated
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ringusTheImp/darkScribe-daredevil-8B-abliterated

Use Docker

docker model run hf.co/ringusTheImp/darkScribe-daredevil-8B-abliterated

LM Studio
Jan
Ollama
How to use ringusTheImp/darkScribe-daredevil-8B-abliterated with Ollama:
```
ollama run hf.co/ringusTheImp/darkScribe-daredevil-8B-abliterated
```

Unsloth Studio new

How to use ringusTheImp/darkScribe-daredevil-8B-abliterated with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ringusTheImp/darkScribe-daredevil-8B-abliterated to start chatting

Install 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 ringusTheImp/darkScribe-daredevil-8B-abliterated to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ringusTheImp/darkScribe-daredevil-8B-abliterated to start chatting

Docker Model Runner
How to use ringusTheImp/darkScribe-daredevil-8B-abliterated with Docker Model Runner:
```
docker model run hf.co/ringusTheImp/darkScribe-daredevil-8B-abliterated
```

Lemonade

How to use ringusTheImp/darkScribe-daredevil-8B-abliterated with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ringusTheImp/darkScribe-daredevil-8B-abliterated

Run and chat with the model

lemonade run user.darkScribe-daredevil-8B-abliterated-{{QUANT_TAG}}

List all available models

lemonade list

darkScribe-daredevil-8B-abliterated

I kinda overcooked this. Use for fun, don't think you'll get the most coherent of chats. Was trying to train for dark fantasy, and creative-novel writing. But this was my first fine-tune, and technically it wasn't set up correctly. The training loss was 0.8, so it should still work for basic chats.

I am an undergrad, doing some fine-tuning as a hobby. If you have any helpful ideas please feel free to share them with me at ringusTheImp@gmail.com

temperature = 0.7, top_k = 50, top_p = 0.95 # recommended by mlabonne/daredevil-8B-abliterated -- change as desired

Downloads last month: 34

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ringusTheImp/darkScribe-daredevil-8B-abliterated

Base model

mlabonne/Daredevil-8B

Finetuned

mlabonne/Daredevil-8B-abliterated

Quantized

(10)

this model

ringusTheImp
/

darkScribe-daredevil-8B-abliterated

darkScribe-daredevil-8B-abliterated

temperature = 0.7, top_k = 50, top_p = 0.95 # recommended by mlabonne/daredevil-8B-abliterated -- change as desired

Model tree for ringusTheImp/darkScribe-daredevil-8B-abliterated

Datasets used to train ringusTheImp/darkScribe-daredevil-8B-abliterated