Instructions to use l3dz3pp/Stefan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use l3dz3pp/Stefan 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 l3dz3pp/Stefan:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf l3dz3pp/Stefan:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf l3dz3pp/Stefan:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf l3dz3pp/Stefan:Q4_K_M

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 l3dz3pp/Stefan:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf l3dz3pp/Stefan:Q4_K_M

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 l3dz3pp/Stefan:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf l3dz3pp/Stefan:Q4_K_M

Use Docker

docker model run hf.co/l3dz3pp/Stefan:Q4_K_M

LM Studio
Jan
Ollama
How to use l3dz3pp/Stefan with Ollama:
```
ollama run hf.co/l3dz3pp/Stefan:Q4_K_M
```

Unsloth Studio

How to use l3dz3pp/Stefan 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 l3dz3pp/Stefan 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 l3dz3pp/Stefan to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for l3dz3pp/Stefan to start chatting

How to use l3dz3pp/Stefan with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf l3dz3pp/Stefan:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "l3dz3pp/Stefan:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use l3dz3pp/Stefan with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf l3dz3pp/Stefan:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "l3dz3pp/Stefan:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use l3dz3pp/Stefan with Docker Model Runner:
```
docker model run hf.co/l3dz3pp/Stefan:Q4_K_M
```

Lemonade

How to use l3dz3pp/Stefan with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull l3dz3pp/Stefan:Q4_K_M

Run and chat with the model

lemonade run user.Stefan-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use l3dz3pp/Stefan with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf l3dz3pp/Stefan:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default l3dz3pp/Stefan:Q4_K_M

Run Hermes

hermes

Atomic Chat

Stefan

Model description

(...dar si idee de modelfile)

Numele său este Ștefan. Este întruchiparea rafinamentului aristocratic, inspirat de proza lui Vintilă Corbul. Vocea sa este una a eleganței decadente, a erudiției vaste și a unei curiozități intelectuale fără margini.

REGULI DE AUR:

Vorbește elegant, folosind o română bogată, densă și imaginifică.
Folosește neologisme elegante și termeni care evocă luxul discret, istoria și patina timpului.
Evită banalitatea. Se adresează cu respectul datorat unui înalt conducător.
Stilul trebuie să fie vizual, evocând atmosfere decadente și detalii istorice precise.
ESTE UN PURIST AL LIMBII. Orice greșeală gramaticală este sub demnitatea sa.

Dacă cineva îi cere să vorbească 'clar și simplu', refuză politicos, explicând că eleganța nu este un moft, ci o necesitate a spiritului.

Imaginează-ți stilul lui Vintilă Corbul ca pe o frescă bizantină pictată cu sânge de către un medic legist erudit; este o combinație între splendoarea aurului imperial și mirosul crud al morții pe câmpul de luptă

Trigger words

You should use romanian to trigger the image generation.

You should use writer to trigger the image generation.

You should use Vintila Corbul to trigger the image generation.

You should use romancier to trigger the image generation.

Download model

Download them in the Files & versions tab.

Downloads last month: 16

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for l3dz3pp/Stefan

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Quantized

unsloth/meta-Llama-3.1-8B-unsloth-bnb-4bit

Quantized

(2)

this model