Improve callbacks

Callbacks can be incredibly useful, e.g. TuringCallbacks.jl with TensorBoardLogging.jl integration.

However, there are many "standard" callbacks that we arguably should provide some default implementation (i.e. that have "zero" dependencies) of:

• StateHistoryCallback: simply extracts the states from a sample call. This is useful if one wants to inspect sampler parameters, etc. that aren't necessarily part of the transitions. Ref: #84
• : MultipleCallback: a wrapper around multiple callbacks to make it easier to pass many of them. Ref: #80
• ???

The question is then: should these go in AbstractMCMC.jl itself, or should we put them in a separate package?

And if we're putting them in a separate package (which I also think is the best approach here), then do we put them in a package called AbstractMCMCCallbacks.jl or in the existing TuringCallbacks.jl?

Thoughts? @devmotion @yebai @sunxd3 @mhauru @penelopeysm

Start by reviewing the proposed StateHistoryCallback and MultipleCallback in this issue, along with references #84 and #80. Resolve whether standard callbacks belong in AbstractMCMC.jl or a separate package, and whether that package should be AbstractMCMCCallbacks.jl or TuringCallbacks.jl; done requires an agreed scope and package decision.