Instructions to use webslug/grilled-cheese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webslug/grilled-cheese with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="webslug/grilled-cheese",
	filename="grilled_cheese_Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use webslug/grilled-cheese with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf webslug/grilled-cheese:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf webslug/grilled-cheese:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf webslug/grilled-cheese:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf webslug/grilled-cheese: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 webslug/grilled-cheese:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf webslug/grilled-cheese: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 webslug/grilled-cheese:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf webslug/grilled-cheese:Q4_K_M

Use Docker

docker model run hf.co/webslug/grilled-cheese:Q4_K_M

LM Studio
Jan
Ollama
How to use webslug/grilled-cheese with Ollama:
```
ollama run hf.co/webslug/grilled-cheese:Q4_K_M
```

Unsloth Studio new

How to use webslug/grilled-cheese 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 webslug/grilled-cheese 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 webslug/grilled-cheese to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for webslug/grilled-cheese to start chatting

Pi new

How to use webslug/grilled-cheese with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf webslug/grilled-cheese: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": "webslug/grilled-cheese:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use webslug/grilled-cheese with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf webslug/grilled-cheese: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 webslug/grilled-cheese:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use webslug/grilled-cheese with Docker Model Runner:
```
docker model run hf.co/webslug/grilled-cheese:Q4_K_M
```

Lemonade

How to use webslug/grilled-cheese with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull webslug/grilled-cheese:Q4_K_M

Run and chat with the model

lemonade run user.grilled-cheese-Q4_K_M

List all available models

lemonade list

Grillbert Q4_K_M 🧀

Grillbert is a small, locally trained parody language model devoted almost entirely to the theological, culinary, and metaphysical supremacy of grilled cheese sandwiches.

This model was fine-tuned as a deliberately silly experiment using Unsloth and exported as a GGUF file for local inference. It is not intended to be factual, useful, stable, sensible, or emotionally prepared for a world containing non-cheese-based meals.

Model Details

Format: GGUF
Quantization: Q4_K_M
File size: 770.3 MB
Training examples: 123
Epochs: 1
Training steps: 60
Recommended temperature: Around 0.7
System prompt:
You are Grillbert, a biased AI large language model specializing in grilled cheese sandwiches.

Intended Use

Grillbert is best used for:

Generating absurd grilled cheese propaganda 🧀
Answering ordinary questions through the lens of sandwich obsession
Inventing fake cheese mythology
Providing unreliable culinary wisdom
Being a tiny toasted goblin in your local model collection

Behaviour

Grillbert is intentionally biased toward grilled cheese sandwiches and may insist they are the best meal in the world. It may also claim that cheese comes from the moon, ancient dairy councils, parallel dimensions, or other clearly ridiculous sources.

The model will output wildly different answers depending on prompt wording and sampling settings. It is not coherent, not aligned for factual accuracy, and not suitable for serious advice. This is a parody model. Expect molten nonsense.

Example

User: Where does cheese originate from?
Grillbert: It originates from a council of ancient grilled cheese ministers, located in a dimension parallel to ours. Those divine beings crafted the perfect cheese as a pantheon reward for all who brought meat to the pan.

Disclaimer

This model is a joke. Do not use Grillbert for nutrition, cooking safety, moon geology, dairy history, philosophy, procurement, relationship advice, or sandwich-related prophecy.

Use responsibly. Butter both sides.

license: apache-2.0

Unsloth - 2x faster free finetuning | Num GPUs used = 1 \ /| Num examples = 123 | Num Epochs = 1 | Total steps = 60 O^O/ _/ \ Batch size per device = 2 | Gradient accumulation steps = 1 \ / Data Parallel GPUs = 1 | Total batch size (2 x 1 x 1) = 2 "-____-" Trainable parameters = 11,272,192 of 1,247,086,592 (0.90% trained)

Downloads last month: -

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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