# How to save multivariate distribution generated by using variational inference with the help of Turing package?

**URL:** <https://discourse.julialang.org/t/how-to-save-multivariate-distribution-generated-by-using-variational-inference-with-the-help-of-turing-package/42300>\
**Category:** New to Julia\
**Tags:** turing, distributions\
**Created:** [June 30, 2020, 1:22pm UTC](https://discourse.julialang.org/t/how-to-save-multivariate-distribution-generated-by-using-variational-inference-with-the-help-of-turing-package/42300 "2020-06-30T13:22:38Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Manu\_Francis](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/manu_francis/32/10010_2.png) [@Manu\_Francis](https://discourse.julialang.org/u/Manu_Francis)\
**Post date:** [June 30, 2020, 1:22pm UTC](https://discourse.julialang.org/t/how-to-save-multivariate-distribution-generated-by-using-variational-inference-with-the-help-of-turing-package/42300/1 "2020-06-30T13:22:38Z")

</div>

Hi,  
I am trying to save the multivariate distribution generated by using variational inference. I tried to save in JLS format. But I am getting the following error:

`ERROR: MethodError: no method matching write(::IOStream, ::Bijectors.TransformedDistribution{DistributionsAD.TuringDiagMvNormal{Array{Float64,1},Array{Float64,1}},Bijectors.Stacked{Tuple{Bijectors.Exp{0},Bijectors.Identity{0}},2},Multivariate})`

The minimum working example is as below:

```julia
using Random
using Turing
using Turing: Variational

Random.seed!(42);
# generate data, n = 2000
x = randn(2000);
@model model(x) = begin
    s ~ InverseGamma(2, 3)
    m ~ Normal(0.0, sqrt(s))
    for i = 1:length(x)
        x[i] ~ Normal(m, sqrt(s))
    end
end
# construct model
m = model(x);

# ADVI
advi = ADVI(10, 1000)
q = vi(m, advi);

#save
write("chain.jls", q)

```

If I am wrong, is there any other packages available to store multivariate distribution?

Thanks in Advance !  
Manu