Instructions to use Angshul/higher-order-pruner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Angshul/higher-order-pruner with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Angshul/higher-order-pruner", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pyproject.toml from Angshul/higher-order-pruner: direct link, hf CLI and curl.
- Browser
- Download file 679 Bytes
-
https://huggingface.co/Angshul/higher-order-pruner/resolve/main/pyproject.toml
- Command line
-
hf download hf://Angshul/higher-order-pruner/pyproject.toml
-
curl -L -o pyproject.toml https://huggingface.co/Angshul/higher-order-pruner/resolve/main/pyproject.toml
679 Bytes
| [build-system] | |
| requires = ["setuptools>=70", "wheel"] | |
| build-backend = "setuptools.build_meta" | |
| [project] | |
| name = "higher-order-pruner" | |
| version = "0.1.0" | |
| description = "Model-agnostic higher-order pruning for PyTorch and Hugging Face models" | |
| readme = "README.md" | |
| requires-python = ">=3.10" | |
| license = {text = "Apache-2.0"} | |
| authors = [{name = "Angshul Majumdar"}] | |
| dependencies = [ | |
| "torch>=2.4,<3", | |
| "transformers>=4.57,<5", | |
| "accelerate>=1.2,<2", | |
| "safetensors>=0.5,<1", | |
| "huggingface_hub>=0.34,<2", | |
| ] | |
| [project.optional-dependencies] | |
| test = ["pytest>=8,<10"] | |
| [tool.setuptools.packages.find] | |
| include = ["higher_order_pruner*"] | |
| [tool.pytest.ini_options] | |
| testpaths = ["tests"] | |