Add `to_distribution` for Hidden Markov Models and BUGS models

[yebai]

Copied from #595 (comment)

HMMs can be straightforwardly supported via the new to_distribution interface:

"""
           hmm(K, T)

       A Hidden Markov Model with `K` states and `T` observations with marginalized hidden states.
       """
       @model function hmm(K, T)
           # Transition matrix.
           π ~ product_distribution(fill(Dirichlet(fill(1 / K, K)), K))
           # Mean of emission distribution.
           μ ~ Bijectors.ordered(MvNormal(zeros(K), 10I))

           # HMM(init, trans, emissions).
           hmm = HMM(π[:, 1], permutedims(π), Normal.(μ, 1))
           y ~ to_distribution(hmm, T)

           return y
       end

For to_distribution(hmm, T), we need to implement two methods, i.e.,

• rand(to_distribution(hmm, T)) which samples y of length T
• log pdf (to_distribution(hmm), y), which computes the marginal log density of y by the forward-backward algorithm.