ggml_opt_step_adamw method

Pointer<ggml_tensor> ggml_opt_step_adamw(Pointer<ggml_context> ctx, Pointer<ggml_tensor> a, Pointer<ggml_tensor> grad, Pointer<ggml_tensor> m, Pointer<ggml_tensor> v, Pointer<ggml_tensor> adamw_params,)

AdamW optimizer step Paper: https://arxiv.org/pdf/1711.05101v3.pdf PyTorch: https://pytorch.org/docs/stable/generated/torch.optim.AdamW.html

Implementation

ffi.Pointer<ggml_tensor> ggml_opt_step_adamw(
  ffi.Pointer<ggml_context> ctx,
  ffi.Pointer<ggml_tensor> a,
  ffi.Pointer<ggml_tensor> grad,
  ffi.Pointer<ggml_tensor> m,
  ffi.Pointer<ggml_tensor> v,
  ffi.Pointer<ggml_tensor> adamw_params,
) {
  return _ggml_opt_step_adamw(
    ctx,
    a,
    grad,
    m,
    v,
    adamw_params,
  );
}