Instructions to use deepsafe/deepsafe-services with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use deepsafe/deepsafe-services with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("deepsafe/deepsafe-services", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download ensemble-core/main.py from deepsafe/deepsafe-services: direct link, hf CLI and curl.
- Browser
- Download file 553 Bytes
-
https://huggingface.co/deepsafe/deepsafe-services/resolve/main/ensemble-core/main.py
- Command line
-
hf download hf://deepsafe/deepsafe-services/ensemble-core/main.py
-
curl -L -o main.py https://huggingface.co/deepsafe/deepsafe-services/resolve/main/ensemble-core/main.py
553 Bytes
| from typing import Any, Dict | |
| from fastapi import FastAPI | |
| from pydantic import BaseModel | |
| app = FastAPI(title="Ensemble Core Service") | |
| class EnsembleRequest(BaseModel): | |
| media_type: str | |
| model_results: Dict[str, Any] | |
| method: str = "stacking" | |
| async def calculate_ensemble(request: EnsembleRequest): | |
| # TODO: Migrate proprietary ensemble logic from gateway | |
| return {"verdict": "fake", "confidence": 0.95, "method_used": request.method} | |
| async def health(): | |
| return {"status": "healthy"} | |