diff --git a/src/Flux.jl b/src/Flux.jl
index 3b4b4b9237..afa47f6fc0 100644
--- a/src/Flux.jl
+++ b/src/Flux.jl
@@ -24,7 +24,7 @@ export Chain, Dense, Embedding, Maxout, SkipConnection, Parallel, PairwiseFusion
        AdaptiveMaxPool, AdaptiveMeanPool, GlobalMaxPool, GlobalMeanPool, MaxPool, MeanPool,
        Dropout, AlphaDropout, LayerNorm, BatchNorm, InstanceNorm, GroupNorm,
        Upsample, PixelShuffle,
-       fmap, cpu, gpu, f32, f64,
+       fmap, cpu, gpu, f32, f64, rand32, randn32, zeros32, ones32,
        testmode!, trainmode!
 
 include("optimise/Optimise.jl")
diff --git a/src/train.jl b/src/train.jl
index a18b1db59e..90bec2534b 100644
--- a/src/train.jl
+++ b/src/train.jl
@@ -27,7 +27,7 @@ It differs from `Optimisers.setup` in that it:
 
 # Example
 ```jldoctest
-julia> model = Dense(2=>1, leakyrelu; init=Flux.ones32);
+julia> model = Dense(2=>1, leakyrelu; init=ones32);
 
 julia> opt_state = Flux.setup(Momentum(0.1), model)  # this encodes the optimiser and its state
 (weight = Leaf(Momentum{Float64}(0.1, 0.9), Float32[0.0 0.0]), bias = Leaf(Momentum{Float64}(0.1, 0.9), Float32[0.0]), σ = ())