Encoder in language model vs encoder+classifer

Part 2 (2019)
1

I was going through the language model and the classifier code in the fastai library.
Curious as to why -

  1. Language model encoder is this -
    encoder = arch(vocab_sz, **config)

  2. Classification encoder is multiBatch -
    encoder = MultiBatchEncoder(bptt, max_len, arch(vocab_sz, **config), pad_idx=pad_idx)

2

Preliminary guess without looking at the source code (so what im saying next could be wrong).

In classification the text is pretty long, so you gotta do a MultiBatchEncoder, otherwise it doesn’t fit in memory (you’ll probably have to check the source code to further understand what this multibatchencoder does, but in short it runs a parts of the sentence batch by batch, connecting them through hidden states) . But in an LM things arent that long, in fact the data is cut into nice pieces depending on the bs and bptt and it just works.