Instructions to use replicate/adam-atan2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/adam-atan2 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/adam-atan2", version=1) - Notebooks
- Google Colab
- Kaggle
Download torch-ext/torch_binding.h from replicate/adam-atan2: direct link, hf CLI and curl.
- Browser
- Download file 387 Bytes
-
https://huggingface.co/replicate/adam-atan2/resolve/main/torch-ext/torch_binding.h
- Command line
-
hf download hf://replicate/adam-atan2/torch-ext/torch_binding.h
-
curl -L -o torch_binding.h https://huggingface.co/replicate/adam-atan2/resolve/main/torch-ext/torch_binding.h
387 Bytes
| namespace adam_atan2 { | |
| void adam_atan2_cuda_impl_( | |
| std::vector<at::Tensor> params, | |
| std::vector<at::Tensor> grads, | |
| std::vector<at::Tensor> exp_avgs, | |
| std::vector<at::Tensor> exp_avg_sqs, | |
| std::vector<at::Tensor> state_steps, | |
| const double lr, | |
| const double beta1, | |
| const double beta2, | |
| const double weight_decay); | |
| } | |