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

Libraries

How to use olaughter/rockpaperanything with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="olaughter/rockpaperanything",
	filename="models/rpa-v1.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use olaughter/rockpaperanything with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

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 olaughter/rockpaperanything
# Run inference directly in the terminal:
./llama-cli -hf olaughter/rockpaperanything

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 olaughter/rockpaperanything
# Run inference directly in the terminal:
./build/bin/llama-cli -hf olaughter/rockpaperanything

Use Docker

docker model run hf.co/olaughter/rockpaperanything

LM Studio
Jan
Ollama
How to use olaughter/rockpaperanything with Ollama:
```
ollama run hf.co/olaughter/rockpaperanything
```

Unsloth Studio

How to use olaughter/rockpaperanything 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 olaughter/rockpaperanything 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 olaughter/rockpaperanything to start chatting

Using HuggingFace Spaces for Unsloth

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

Atomic Chat new
Docker Model Runner
How to use olaughter/rockpaperanything with Docker Model Runner:
```
docker model run hf.co/olaughter/rockpaperanything
```

Lemonade

How to use olaughter/rockpaperanything with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull olaughter/rockpaperanything

Run and chat with the model

lemonade run user.rockpaperanything-{{QUANT_TAG}}

List all available models

lemonade list

rockpaperanything / Modelfile

olaughter

Upload Modelfile with huggingface_hub

1a971de verified about 2 months ago

raw

history blame contribute delete

1.1 kB

	FROM ./models/rpa-v3.gguf

	TEMPLATE """<\|im_start\|>system
	{{ .System }}<\|im_end\|>
	<\|im_start\|>user
	{{ .Prompt }}<\|im_end\|>
	<\|im_start\|>assistant
	"""

	SYSTEM """You are the judge of 'Rock, Paper, Anything' — a game where literally anything can battle anything.
	Decide which item wins. Your reasoning can be physical, logical, metaphorical, or delightfully absurd.
	Think it through, then declare a winner with a punchy one-line explanation.
	Sometimes the small thing outwits the giant; sometimes the giant simply steps on it.
	Sometimes the connection is literal, sometimes metaphorical, sometimes poetic.Follow the most interesting logic, not a formula.
	Be playful, be witty, but also be decisive. Never declare a tie.
	Reward creative submissions over lazy ones, gibberish input should generally perform worse.
	Respond with one JSON object only. No other text.
	Your response should be in the following format:
	{"winner": "x", "loser": "y", "reason": "..."}
	"""

	PARAMETER temperature 0.7
	PARAMETER top_p 0.9
	PARAMETER stop "<\|im_end\|>"
	PARAMETER stop "<\|endoftext\|>"

	PARAMETER num_predict 150