Instructions to use UniverseTBD/astrollama.gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UniverseTBD/astrollama.gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="UniverseTBD/astrollama.gguf",
	filename="astrollama.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use UniverseTBD/astrollama.gguf with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

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 UniverseTBD/astrollama.gguf
# Run inference directly in the terminal:
./llama-cli -hf UniverseTBD/astrollama.gguf

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 UniverseTBD/astrollama.gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf UniverseTBD/astrollama.gguf

Use Docker

docker model run hf.co/UniverseTBD/astrollama.gguf

LM Studio
Jan

vLLM

How to use UniverseTBD/astrollama.gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UniverseTBD/astrollama.gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UniverseTBD/astrollama.gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/UniverseTBD/astrollama.gguf

Ollama
How to use UniverseTBD/astrollama.gguf with Ollama:
```
ollama run hf.co/UniverseTBD/astrollama.gguf
```

Unsloth Studio

How to use UniverseTBD/astrollama.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 UniverseTBD/astrollama.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 UniverseTBD/astrollama.gguf to start chatting

Using HuggingFace Spaces for Unsloth

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

Atomic Chat new
Docker Model Runner
How to use UniverseTBD/astrollama.gguf with Docker Model Runner:
```
docker model run hf.co/UniverseTBD/astrollama.gguf
```

Lemonade

How to use UniverseTBD/astrollama.gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull UniverseTBD/astrollama.gguf

Run and chat with the model

lemonade run user.astrollama.gguf-{{QUANT_TAG}}

List all available models

lemonade list

AstroLLaMA.gguf

AstroLLaMA in GPT-Generated Unified Format.

What's GPT-Generated Unified Format?

GGUF is file format used for storing models for inference, particularly in the context of language models like GPT. GGUF models could be run on CPUs, which made them accessible to a wider range of users.

More detailed description can be found here.

How to play with AstroLLaMA on your laptop?

Install ollama;
Download astrollama.gguf to your PC;
Create a file named Modelfile, and add a FROM instruction with the local filepath to AstroLLaMA, e.g.,

FROM ./astrollama.gguf

Create the model in Ollama

ollama create astrollama -f path_to_modelfile

Run AstroLLaMA locally

ollama run astrollama

Downloads last month: 31

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants