[spam] [personal] perceiver model notes

[k]

so a perceiver model is:
input ->
preprocessor ->
encoder [required] ->
decoder [processes encoded and unencoded input together] ->
postprocessor ->
output

let's see how the encoder is constructed in PerceiverModel.__init__:
self.embeddings = PerceiverEmbeddings()
self.encoder = PerceiverEncoder(kv_dim)

So most of the functionality of a perceiver model is in the
PerceiverEncoder class.