h SSKJrJrJr SSKJrJrJrJrJ r J r J r J r J r JrJrJrJr SSKJrJr SSKJr SSKJr SSKJr SS \\\44S jjrS \S \\\44S jrS\\\\\4S\\\4S\\\4S \\\\\4\44Sjrg ))ListTuplecast) LinearLogisticMaxoutModelchain concatenateglorot_uniform_init list2ragged reduce_first reduce_last reduce_max reduce_mean with_getitem)Floats2dRagged)Doc)registry) extract_spansNreturncB[[X[S9[55$)zjAn output layer for multi-label classification. It uses a linear layer followed by a logistic activation. )nOnIinit_W)r rr r)rrs Q/home/james-whalen/.local/lib/python3.13/site-packages/spacy/ml/models/spancat.pybuild_linear_logisticr s 2-@A8: NN hidden_sizec [[[[[[ 4[ 55[[[[ 4[55[5[55[USSS95$)zReduce sequences by concatenating their mean and max pooled vectors, and then combine the concatenated vectors with a hidden layer. Tg)r normalizedropout) r r rr rrrrrrr)r"s rbuild_mean_max_reducerr& s]  vx'(+- 8 vx'(,. 9 M L  +s; r!tok2vecreducerscorerc[[[[[[ [ 4[[ [ 44[S[U[[[[[ 4[55555[5UU5nURSU5 URSU5 URSU5 U$)ayBuild a span categorizer model, given a token-to-vector model, a reducer model to map the sequence of vectors for each span down to a single vector, and a scorer model to map the vectors to probabilities. tok2vec (Model[List[Doc], List[Floats2d]]): The tok2vec model. reducer (Model[Ragged, Floats2d]): The reducer model. scorer (Model[Floats2d, Floats2d]): The scorer model. rr'r(r)) r rr rrrrrrr rset_ref)r'r(r)models rbuild_spancat_modelr-/s  %S 6)*E&&.,AA B 5$uT(^V-C'Dkm"TU   E MM)W% MM)W% MM(F# Lr!)NN)typingrrr thinc.apirrrr r r r r rrrrr thinc.typesrrtokensrutilrrr intr&r-r!rr5s$$))OuXx5G/HO  fh6F0G  49d8n, - 68# $ (H$ % 5cF" #X -. r!