--- license: apache-2.0 library_name: pruna-engine thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg" metrics: - memory_disk - memory_inference - inference_latency - inference_throughput - inference_CO2_emissions - inference_energy_consumption ---
PrunaAI
# Simply make AI models cheaper, smaller, faster, and greener! [![Twitter](https://img.shields.io/twitter/follow/PrunaAI?style=social)](https://twitter.com/PrunaAI) [![GitHub](https://img.shields.io/github/followers/PrunaAI?label=Follow%20%40PrunaAI&style=social)](https://github.com/PrunaAI) [![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-blue)](https://www.linkedin.com/company/93832878/admin/feed/posts/?feedType=following) - Give a thumbs up if you like this model! - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact). - Request access to easily compress your *own* AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai). - Read the documentations to know more [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/) - Share feedback and suggestions on the Slack of Pruna AI (Coming soon!). ## Results ![image info](./plots.png) **Important remarks:** - The quality of the model output might slightly vary compared to the base model. There might be minimal quality loss. - These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in config.json and are obtained after a hardware warmup. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). - You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai). ## Setup You can run the smashed model with these steps: 0. Check cuda, torch, packaging requirements are installed. For cuda, check with `nvcc --version` and install with `conda install nvidia/label/cuda-12.1.0::cuda`. For packaging and torch, run `pip install packaging torch`. 1. Install the `pruna-engine` available [here](https://pypi.org/project/pruna-engine/) on Pypi. It might take 15 minutes to install. ```bash pip install pruna-engine[gpu] --extra-index-url https://pypi.nvidia.com --extra-index-url https://pypi.ngc.nvidia.com --extra-index-url https://prunaai.pythonanywhere.com/ ``` 3. Download the model files using one of these three options. - Option 1 - Use command line interface (CLI): ```bash mkdir Linaqruf-animagine-xl-turbo-green-smashed huggingface-cli download PrunaAI/Linaqruf-animagine-xl-turbo-green-smashed --local-dir Linaqruf-animagine-xl-turbo-green-smashed --local-dir-use-symlinks False ``` - Option 2 - Use Python: ```python import subprocess repo_name = "Linaqruf-animagine-xl-turbo-green-smashed" subprocess.run(["mkdir", repo_name]) subprocess.run(["huggingface-cli", "download", 'PrunaAI/'+ repo_name, "--local-dir", repo_name, "--local-dir-use-symlinks", "False"]) ``` - Option 3 - Download them manually on the HuggingFace model page. 3. Load & run the model. ```python from pruna_engine.PrunaModel import PrunaModel model_path = "Linaqruf-animagine-xl-turbo-green-smashed/model" # Specify the downloaded model path. smashed_model = PrunaModel.load_model(model_path) # Load the model. smashed_model(prompt='Beautiful fruits in trees', height=1024, width=1024)[0][0] # Run the model where x is the expected input of. ``` ## Configurations The configuration info are in `config.json`. ## License We follow the same license as the original model. Please check the license of the original model Linaqruf/animagine-xl before using this model. ## Want to compress other models? - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact). - Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).