Instructions to use replicate/mrope_get_position_ids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/mrope_get_position_ids 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/mrope_get_position_ids", version=1) - Notebooks
- Google Colab
- Kaggle
Download build.toml from replicate/mrope_get_position_ids: direct link, hf CLI and curl.
- Browser
- Download file 345 Bytes
-
https://huggingface.co/replicate/mrope_get_position_ids/resolve/main/build.toml
- Command line
-
hf download hf://replicate/mrope_get_position_ids/build.toml
-
curl -L -o build.toml https://huggingface.co/replicate/mrope_get_position_ids/resolve/main/build.toml
345 Bytes
| [general] | |
| name = "get_position_ids" | |
| [torch] | |
| src = [ | |
| "ext-torch/torch_binding.cpp", | |
| "ext-torch/torch_binding.h", | |
| ] | |
| include = ["."] | |
| pyext = ["py", "json"] | |
| [kernel.get_position_ids] | |
| cuda-capabilities = ["7.0", "7.2", "7.5", "8.0", "8.6", "8.7", "8.9", "9.0"] | |
| src = ["get_position_ids/get_position_ids.cu"] | |
| include = ["."] | |
| depends = ["torch"] | |