Instructions to use Wizz13150/WizzGPTv6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Wizz13150/WizzGPTv6 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Wizz13150/WizzGPTv6",
	filename="WizzGPTv6.Q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Wizz13150/WizzGPTv6 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Wizz13150/WizzGPTv6:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Wizz13150/WizzGPTv6:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Wizz13150/WizzGPTv6:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Wizz13150/WizzGPTv6: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 Wizz13150/WizzGPTv6:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Wizz13150/WizzGPTv6: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 Wizz13150/WizzGPTv6:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Wizz13150/WizzGPTv6:Q8_0

Use Docker

docker model run hf.co/Wizz13150/WizzGPTv6:Q8_0

LM Studio
Jan
Ollama
How to use Wizz13150/WizzGPTv6 with Ollama:
```
ollama run hf.co/Wizz13150/WizzGPTv6:Q8_0
```

Unsloth Studio new

How to use Wizz13150/WizzGPTv6 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 Wizz13150/WizzGPTv6 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 Wizz13150/WizzGPTv6 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Wizz13150/WizzGPTv6 to start chatting

Docker Model Runner
How to use Wizz13150/WizzGPTv6 with Docker Model Runner:
```
docker model run hf.co/Wizz13150/WizzGPTv6:Q8_0
```

Lemonade

How to use Wizz13150/WizzGPTv6 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Wizz13150/WizzGPTv6:Q8_0

Run and chat with the model

lemonade run user.WizzGPTv6-Q8_0

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

A small GPT2 model to generate prompts for image generation with SDXL, especially ZavyChromaXL, or similar models. Trained from the base model. Attach a Style to affect the render further. Small enough to easily run on any cpu. Pretty instant on a gpu.

Used in text-completion mode, from very short input prompts (A, The, A beautiful, The portrait of [...]) This is not a chatbot.

Settings that I use for a good variety with WizzGPTv6.Q8_0.gguf (173mb) : max_tokens=75, temperature=1.25, top_p=0.90, top_k=40, repeat_penalty=1.4

Examples of generated images gallery : https://civitai.com/user/_Wizz_/images

Downloads last month: 10

GGUF

Model size

0.2B params

Architecture

gpt2

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support