Instructions to use FlyTheGoose/goose-aya-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FlyTheGoose/goose-aya-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FlyTheGoose/goose-aya-gguf",
	filename="goose-aya-Q5_K_M.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 FlyTheGoose/goose-aya-gguf 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 FlyTheGoose/goose-aya-gguf:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf FlyTheGoose/goose-aya-gguf:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FlyTheGoose/goose-aya-gguf:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf FlyTheGoose/goose-aya-gguf:Q5_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 FlyTheGoose/goose-aya-gguf:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf FlyTheGoose/goose-aya-gguf:Q5_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 FlyTheGoose/goose-aya-gguf:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FlyTheGoose/goose-aya-gguf:Q5_K_M

Use Docker

docker model run hf.co/FlyTheGoose/goose-aya-gguf:Q5_K_M

LM Studio
Jan
Ollama
How to use FlyTheGoose/goose-aya-gguf with Ollama:
```
ollama run hf.co/FlyTheGoose/goose-aya-gguf:Q5_K_M
```

Unsloth Studio

How to use FlyTheGoose/goose-aya-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 FlyTheGoose/goose-aya-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 FlyTheGoose/goose-aya-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FlyTheGoose/goose-aya-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use FlyTheGoose/goose-aya-gguf with Docker Model Runner:
```
docker model run hf.co/FlyTheGoose/goose-aya-gguf:Q5_K_M
```

Lemonade

How to use FlyTheGoose/goose-aya-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FlyTheGoose/goose-aya-gguf:Q5_K_M

Run and chat with the model

lemonade run user.goose-aya-gguf-Q5_K_M

List all available models

lemonade list

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

Check out the documentation for more information.

Goose Expanse 32b

"Goose was here. Goose trained this. What came out of it? Goose has no idea. Try it and find out, Goose."

About This Model This is an experimental model bake combining Aya Expanse with a custom LoRA trained on Goose's unique voice and dataset.

Type: LoRA Merge / Baked Quant

Quantization: Q5 K_M (GGUF)

Dataset: Goose Voice & Speech Corpus

Status: Highly experimental, cursed, and unpredictable.

Disclaimer Expect wild responses, unpredictable Goose energy, and odd stylistic quirks. Use at your own risk! 🪿

Downloads last month: 87

GGUF

Model size

32B params

Architecture

command-r

Hardware compatibility

5-bit

Inference Providers NEW

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