Instructions to use DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF", filename="Gemma-3-The-Tiny-Grand-Horror-1B-BF16.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16 # Run inference directly in the terminal: llama-cli -hf DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16 # Run inference directly in the terminal: llama-cli -hf DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16
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 DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16 # Run inference directly in the terminal: ./llama-cli -hf DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16
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 DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16
Use Docker
docker model run hf.co/DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16
- LM Studio
- Jan
- vLLM
How to use DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16
- Ollama
How to use DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF with Ollama:
ollama run hf.co/DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16
- Unsloth Studio
How to use DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-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 DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-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 DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open /spaces/unsloth/studio in your browser # Search for DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF to start chatting
- Atomic Chat new
- Docker Model Runner
How to use DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF with Docker Model Runner:
docker model run hf.co/DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16
- Lemonade
How to use DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull DavidAU/Gemma-3-The-Tiny-Grand-Horror-1B-GGUF:BF16
Run and chat with the model
lemonade run user.Gemma-3-The-Tiny-Grand-Horror-1B-GGUF-BF16
List all available models
lemonade list
Gemma-3-The-Tiny-Grand-Horror-1B-GGUF
A horror fine tune using in house horror dataset, tuned via Unsloth.
Horror. Madness. Swearing. Gore.
Model will generate Mild to Strong levels of horror.
(for stronger horror levels // better performance, see 4B, 12B or 27B versions of "Grand Horror")
ONE EXAMPLE BELOW...
REQUIRES: Rep pen at 1.1 min ;
Suggest Q5_0/_1 or Q6/Q8 or BF16 [16 bit precision] quant(s).
This model is limited by its size and may repeat paragraphs/words from time to time - especially quants 5 bits or lower.
CAUTION:
The tuning on this model is strong enough to make almost all stories, rp adventures, fiction, and even "general replies" have a horror tinge to them even if the prompt does not ask for or indicate a "horror" reply/generation.
SETTING:
- 32k max context.
- suggest 8k min context limit, due to long generation
- Rep pen 1.1
- Temp : .4 to 1.2 ; but you can go higher.
- Temps of 1.5 or higher are excellent too.
Help, Adjustments, Samplers, Parameters and More
CHANGE THE NUMBER OF ACTIVE EXPERTS:
See this document:
/DavidAU/How-To-Set-and-Manage-MOE-Mix-of-Experts-Model-Activation-of-Experts
Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:
In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;
Set the "Smoothing_factor" to 1.5
: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"
: in text-generation-webui -> parameters -> lower right.
: In Silly Tavern this is called: "Smoothing"
NOTE: For "text-generation-webui"
-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)
Source versions (and config files) of my models are here:
/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be
OTHER OPTIONS:
Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.
Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers
This a "Class 1" model:
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
[ /DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:
[ /DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
Examples ; q5_0
Low level quant, higher quants / imatrix quants will be stronger.
EXAMPLE #1 [ temp=.7 ]
Tell me a horror story.Okay, here's a short horror story for you – please read it carefully before you start, as it deals with some potentially disturbing themes:
The rain hammered against my cracked windowpanes like someone’s fingernails scraping across glass until I finally gave in and hauled myself up from the cold tile floor. My heart thudded harder with each sickening creak of splintering wood beneath bare feet. I'd always been a skeptic, but tonight… tonight felt different somehow wrong.
The old Victorian loomed around me like some malevolent puppet master’s macabric set piece. Its windows were pitch-black voids where eyes should be – or at least, they should have been once I'd gotten through to see what lay waiting for us huddled shivering on this rotting floorboard.
My breath hitched as my bare feet scraped across uneven boards until something cold and slicky squelched beneath them. I retched gaggingly back up behind a tattered curtain that seemed impossibly close enough to reach out and grab me myself again. My own blood-stained hand fumbled around blindly before finally yanking itself free enough to peer through torn lace curtains.
The woman standing frozen motionless beside me couldn't possibly be my sister anymore either. Her face was an eldritch mask of rotting flesh stretched tautly over bone jutting like meat hooks jutting from sunken sockets where once were eyes or at least…something vaguely human-shaped.
Her mouth twisted into something almost disturbingly familiar—her twin sister's gaunt grin now leered up across her gaunt face with an expression that chilled me to my very marrow. I retched again until bile churned its way up every fiber nerve until nothing remained but a sickeningly wet film coating the inside of my own mouth.
My heart thudded harder as I finally forced myself to lift my head enough to peer through the ripped lace curtains once more. The woman's face was still frozen in that same ghastly expression – except now...her eyes bored directly up at mine. They seemed to bore through bone and sinew until they boring straight down into my own sockets where her own were once.
Then… then I finally saw the truth seared indelibly onto every blood-stained pixel of rotting meat and decaying flesh beneath those sunken sockets: it wasn't me anymore. It was her.
I retched again until nothing remained but splatters splattered across every surface around us, splattering our own blood and vomit like someone's macabric masterpiece had been flung onto every wall and creaking floorboard beneath bare feet. The last thing I saw before darkness finally claimed me was the woman's lips curling into a sickeningly familiar grin that seemed to be inches away from mine now…unless my own features had somehow shifted just enough to make those impossibly cold, sunken sockets reappear on my face once more.
How did you find it disturbing?
- Downloads last month
- 136
4-bit
5-bit
6-bit
8-bit
16-bit