Instructions to use replicate/scattermoe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/scattermoe with Kernels:
# !pip install kernels from kernels import get_kernel # a version (or an explicit revision) is required; see the "Files and versions" tab for the available ones kernel = get_kernel("replicate/scattermoe", version=1) - Notebooks
- Google Colab
- Kaggle
Download build/torch-cuda/__init__.py from replicate/scattermoe: direct link, hf CLI and curl.
- Browser
- Download file 296 Bytes
-
https://huggingface.co/replicate/scattermoe/resolve/main/build/torch-cuda/__init__.py
- Command line
-
hf download hf://replicate/scattermoe/build/torch-cuda/__init__.py
-
curl -L -o __init__.py https://huggingface.co/replicate/scattermoe/resolve/main/build/torch-cuda/__init__.py
296 Bytes
| from .parallel_experts import flatten_sort_count, parallel_linear, ParallelExperts | |
| from . import parallel_experts | |
| from . import kernels | |
| from . import layers | |
| __all__ = [ | |
| "flatten_sort_count", | |
| "parallel_linear", | |
| "ParallelExperts", | |
| "parallel_experts", | |
| "kernels", | |
| "layers" | |
| ] | |