nsfw

Not-For-All-Audiences

Instructions to use Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF", dtype="auto")

llama-cpp-python

How to use Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF",
	filename="pandemonium-3.2-1b-q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0

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 Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0

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 Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF with Ollama:
```
ollama run hf.co/Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0
```

Unsloth Studio

How to use Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF 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 Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF 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 Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0
```

Lemonade

How to use Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Novaciano/Pandemonium-3.2-1B-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.Pandemonium-3.2-1B-Q8_0-GGUF-Q8_0

List all available models

lemonade list

Pandemonium 3.2 1B

La palabra, traducida libremente como todos los demonios, es el nombre inventado por John Milton para la capital del Infierno, "la Alta Capital, de Satán y sus acólitos", construida por los ángeles caídos por indicación de Mammon al final del Libro I de El paraíso perdido (1667).

Sobre el modelo / About this model

ESPAÑOL

Lo básico: Lo probé recien y está sin censura.

Este més hice muchas mezclas; algunas con mayor y otras con menor éxito. Los más grande no siempre significa calidad. O puede tener calidad, si, pero con una censura muy mejorada.

Este modelo es una especie de reinicio, un intento de mejora de mi primer modelo "La-Mejor-Mezcla" que irónicamente fue el mejor intento de minimización de censura por medio de mezclas.

Espero que lo disfruten.

ENGLISH

The basics: I just tried it and it's uncensored.

This month I've made a lot of mixes; some with greater and others with lesser success. Bigger doesn't always mean quality. Or it can mean quality, yes, but with much improved censorship.

This model is a reboot of sorts, an attempt to improve upon my first "La-Mejor-Mezcla" model, which ironically was the best attempt at minimizing censorship through mixes.

I hope you enjoy it.