hSSKJrJrJr SSKJrJrJrJrJ r J r SSK J r SSK Jr SSKJr SSKJr SSKJr S S KJr S S KJr SS \\\\\ 4S\SS\S\S\S\S\\S\4SjjrSrSrSrSrSr g ))ListOptionalcast)LinearModelchain list2arrayuse_ops zero_init)Floats2d)Literal)Errors)Doc)registryPrecomputableAffine)TransitionModelNtok2vec state_type)parsernerextra_state_tokens hidden_width maxout_pieces use_uppernOreturnc"US:Xa U(aSOSnO8US:Xa U(aSOSnO&[[RRUS95eUR S5(aUR S5OS n[ U[5[X855nURSU5 [U(aUOUUUR S5US 9n S n U(a[S 5 [US S 9n S S S 5 [X U [5$!,(df  N=f) a Build a transition-based parser model. Can apply to NER or dependency-parsing. Transition-based parsing is an approach to structured prediction where the task of predicting the structure is mapped to a series of state transitions. You might find this tutorial helpful as background: https://explosion.ai/blog/parsing-english-in-python The neural network state prediction model consists of either two or three subnetworks: * tok2vec: Map each token into a vector representations. This subnetwork is run once for each batch. * lower: Construct a feature-specific vector for each (token, feature) pair. This is also run once for each batch. Constructing the state representation is then simply a matter of summing the component features and applying the non-linearity. * upper (optional): A feed-forward network that predicts scores from the state representation. If not present, the output from the lower model is used as action scores directly. tok2vec (Model[List[Doc], List[Floats2d]]): Subnetwork to map tokens into vector representations. state_type (str): String value denoting the type of parser model: "parser" or "ner" extra_state_tokens (bool): Whether or not to use additional tokens in the context to construct the state vector. Defaults to `False`, which means 3 and 8 for the NER and parser respectively. When set to `True`, this would become 6 feature sets (for the NER) or 13 (for the parser). hidden_width (int): The width of the hidden layer. maxout_pieces (int): How many pieces to use in the state prediction layer. Recommended values are 1, 2 or 3. If 1, the maxout non-linearity is replaced with a ReLu non-linearity if use_upper=True, and no non-linearity if use_upper=False. use_upper (bool): Whether to use an additional hidden layer after the state vector in order to predict the action scores. It is recommended to set this to False for large pretrained models such as transformers, and True for smaller networks. The upper layer is computed on CPU, which becomes a bottleneck on larger GPU-based models, where it's also less necessary. nO (int or None): The number of actions the model will predict between. Usually inferred from data at the beginning of training, or loaded from disk. r rr )valuerNrnFnInPcpurr') ValueErrorrE917formathas_dimget_dimrr rset_dim _define_lowerr _define_upperr resize_output) rrrrrrrnr_feature_tokens t2v_widthloweruppers P/home/james-whalen/.local/lib/python3.13/site-packages/spacy/ml/models/parser.pybuild_tb_parser_modelr9shX"4B! u !3A++*+=>>)0)>)>%DI |'G  OOD,' $<"  ??4   E E U^!RD1E 75- @@^s  D Dc[X[S9$)N)rr'init_W)rr r*s r8r2r2]s Ry 11c[XX#S9$)Nr%rr%s r8r1r1as " ::r<cVURS(a [X5$[X5$)N has_upper)attrs _resize_upper _resize_lower)modelnew_nOs r8r3r3es$ {{;U++  ''r<cHURS5nURS5cURSU5 U$XRS5:XaU$UnUR S5n[ S5 [ XS9nSSS5 URS5(aWRRX5nURRU5nURS5nURS5n URS5(aIURS5n XSU &XSU &[X5H!n URSRU 5 M# URSU5 URSU5 WUR S 'UR#SU5 U$!,(df  GN#=f) Nr7rr'r)r*Wbunseen_classes)get_refr.r0r/ maybe_get_dimr r2 has_paramopsalloc2falloc1f get_paramranger@add set_param_layersset_ref) rCrDr7smallerr'largerlarger_Wlarger_b smaller_W smaller_bold_nOis r8rArAksq MM' "E }}T" dF# ==& & G   t $B &0 ::%%f1::%%f-%%c* %%c*  ??4 __T*F )Wf  )Wf 6* ,-11!4+ h'h'EMM" MM'6" L+ s , F F!cURS5nURS5cURSU5 U$UnURS5nURS5nURS5n[ XXVS9nUR S5(Ga>UR RXQXd5nUR RX5n UR RSXQU5n URS5n URS 5n URS 5n URS5(akURS5nXSS2S U2SS2SS24'XSS2SS2S U2SS24'XS U2SS24'[X5H!nURS RU5 M# URSU5 URS U 5 URS U 5 XpRS'UR!SU5 U$) Nr6rr'r&r()rr'r&r(rFrGpadrrH)rJr.r0rKr1rLrMalloc4frNrPr/rQr@rRrSrTrU)rCrDr6rVr'r&r(rWrXrY larger_padrZr[ smaller_padr\r]s r8rBrBs MM' "E }}T" dF# G   t $B   t $B   t $B f :F::%%b"9::%%f1ZZ''2r: %%c* %%c* ''. ??4 __T*F*3Q&!Q& ',7q!QvXq( )$-QvXq[ !6* ,-11!4+ h'h' +MM! MM'6" Lr<)N)!typingrrr thinc.apirrrr r r thinc.typesr compatrerrorsrtokensrutilr_precomputable_affiner tb_frameworkrboolintr9r2r1r3rArBr<r8rps''JJ 7*LA 49d8n, -LA(LALA LA  LA  LA  LA LA^2;( D!r<