Instructions to use openmodelai/Galactic-2.5-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openmodelai/Galactic-2.5-Mini with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="openmodelai/Galactic-2.5-Mini")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("openmodelai/Galactic-2.5-Mini", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openmodelai/Galactic-2.5-Mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openmodelai/Galactic-2.5-Mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openmodelai/Galactic-2.5-Mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openmodelai/Galactic-2.5-Mini

SGLang

How to use openmodelai/Galactic-2.5-Mini with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "openmodelai/Galactic-2.5-Mini" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openmodelai/Galactic-2.5-Mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "openmodelai/Galactic-2.5-Mini" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openmodelai/Galactic-2.5-Mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openmodelai/Galactic-2.5-Mini with Docker Model Runner:
```
docker model run hf.co/openmodelai/Galactic-2.5-Mini
```

Galactic-2.5-Mini / upload.py

openmodelai

Upload 10 files

1440c49 verified 1 day ago

Raw History Blame Contribute Delete

997 Bytes

	"""Run locally AFTER reviewing the model card and logging in to Hugging Face.
	Creates a private repo by default. No tokens are embedded in this project.
	"""
	import argparse
	from pathlib import Path
	from huggingface_hub import HfApi

	p = argparse.ArgumentParser()
	p.add_argument('--repo', required=True, help='YOUR_NAMESPACE/Galactic-2.5-Mini')
	p.add_argument('--public', action='store_true', help='Create a public repository')
	p.add_argument('--folder', default=str(Path(__file__).resolve().parent/'model'))
	a = p.parse_args()
	if len(a.repo.split('/')) != 2:
	p.error('Use YOUR_NAMESPACE/Galactic-2.5-Mini')
	api = HfApi()
	api.create_repo(repo_id=a.repo, repo_type='model', private=not a.public, exist_ok=True)
	api.upload_folder(repo_id=a.repo, repo_type='model', folder_path=a.folder,
	commit_message='Upload Galactic 2.5 Mini: experimental 50M short-run checkpoint')
	print(f'https://huggingface.co/{a.repo}')
	print('Existing repository visibility is unchanged; check repository Settings.')