nsfw

Not-For-All-Audiences

Instructions to use Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF",
	filename="Tiny-NicoPepper_Conan_Exiles-IQ4_XS.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS

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/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS

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/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS

Use Docker

docker model run hf.co/Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS

LM Studio
Jan
Ollama
How to use Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF with Ollama:
```
ollama run hf.co/Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS
```

Unsloth Studio

How to use Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-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/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-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/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-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/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF with Docker Model Runner:
```
docker model run hf.co/Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS
```

Lemonade

How to use Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF:IQ4_XS

Run and chat with the model

lemonade run user.Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF-IQ4_XS

List all available models

lemonade list

Tiny NicoPepper Conan Exiles

Es un modelo TinyDolphin 1.1b con un dataset inyectado de Conan El Barbaro ⚔️ y otras verduras como H.P. Lovecraft y su contenido de terror cósmico 🌀.

Mi idea principal era inyectar el dataset en un modelo Llama 3.2 1b, pero no admite datasets de formato parquet.

Ideal para ser usado en móviles de gama muy baja.

Lo conforman dos versiones:

IQ4_XS: Es una versión rápida e ideal para celulares pero con un costo minimo de coherencia.
Q5_0: Es una versión mas... digamos... inteligente, pero pide mayor requisitos computacionales. AQUÍ

Elige la versión que más se adapte a tus necesidades.

KoboldCpp

Siguiendo los siguientes pasos te irá tan fluido como se ve abajo.

Nota: Intuíste bien, la primer consulta debe ser "Iniciar Partida".

Inferencia

Solo dejalo en "Default". Igual te dejo los datos por si lo usas en otro programa:

Novaciano
/

Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF

Tiny NicoPepper Conan Exiles

Lo conforman dos versiones:

KoboldCpp

Inferencia

Etiquetas

Model tree for Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF

Datasets used to train Novaciano/Tiny-NicoPepper_Conan_Exiles-IQ4_XS-GGUF