Yes, that is the primary reason why we developed the package in the first place and why we developed it in Fortran; for generic Bayesian inverse problems. All you need to supply is a (likelihood or any density) function that returns the natural logarithm of its scalar value for given input vector and its length,

```
function getLogFunc(ndim, point)
use iso_fortran_env, only: IK => int32, RK => real64
integer(IK), intent(in) :: ndim
real(RK), intent(in) :: point(ndim)
real(RK) :: logFunc
logFunc = -sum(point**2) ! replace this with any complex Bayesian inverse problem.
end function
```

How many parameters does your model have (what is the value of `ndim`

)?

Welcome to the forum, by the way.