iddlmZmZddlmZmZmZmZmZm Z ddl m Z ddl m Z ddlmZddlmZdd lmZdd lmZ dd eeeee fd e ddededededeedefdZdZdZdZdZdZy ))ListOptional)LinearModelchain list2arrayuse_ops zero_init)Floats2d)Literal)Errors)DocPrecomputableAffine)TransitionModelNtok2vec state_type)parsernerextra_state_tokens hidden_width maxout_pieces use_uppernOreturnc|dk(r|rdnd}n5|dk(r|rdnd}n)ttjj||j dr|j dnd }t |tt||}|jd|t|r|n|||j d| } d } |r!td 5t|d } d d d t|| | tS#1swYxYw) 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_dimrrrset_dim _define_lowerr _define_upperr resize_output) rrrrrrrnr_feature_tokens t2v_widthloweruppers g/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/spacy/ml/models/parser.pybuild_tb_parser_modelr7 shX"4B! u !3A++*+=>>)0)>%DI |Y'G  OOD,' $<"  ??4   E E U^ 2!RD1E 2 7E5- @@ 2 2s C00C9c&t||tS)N)rr%init_W)rr r(s r6r0r0\s RBy 11c t||||S)Nr#rr#s r6r/r/`s "r ::r:cP|jdr t||St||S)N has_upper)attrs _resize_upper _resize_lower)modelnew_nOs r6r1r1ds( {{;UF++  ''r:c4|jd}|jd|jd||S||jdk(r|S|}|j d}t d5t ||}ddd|jdrjj||}|jj|}|jd}|jd} |jdrJ|jd} ||d| | |d| t| |D] } |jdj| "|jd||jd||j d <|j#d||S#1swYxYw) Nr5rr%r'r(Wbunseen_classes)get_refr,r.r- maybe_get_dimr r0 has_paramopsalloc2falloc1f get_paramranger>add set_param_layersset_ref) rArBr5smallerr%largerlarger_Wlarger_b smaller_W smaller_bold_nOis r6r?r?js MM' "E }}T" dF# 5==& & G   t $B 1&R01::%%fb1::%%f-%%c* %%c*  ??4 __T*F )HWf  )HWf 66* 5 ,-11!4 5 h'h'EMM" MM'6" L+11s +F  Fc|jd}|jd|jd||S|}|jd}|jd}|jd}t ||||}|j dr?|j j||||}|j j||} |j jd|||} |jd} |jd } |jd } |jdrm|jd}| |ddd |ddddf<| | ddddd |ddf<| | d |ddf<t||D] }|jd j|"|jd||jd | |jd | ||jd<|j!d||S) Nr4rr%r$r&)rr%r$r&rDrEpadrrF)rHr,r.rIr/rJrKalloc4frLrNr-rOr>rPrQrRrS)rArBr4rTr%r$r&rUrVrW larger_padrXrY smaller_padrZr[s r6r@r@s MM' "E }}T" dF# G   t $B   t $B   t $B fr :F::%%b&"b9::%%fb1ZZ''2vr: %%c* %%c* ''. ??4 __T*F*3HQ&!Q& ',7Jq!QvXq( )$-HQvXq[ !66* 5 ,-11!4 5 h'h' +EMM! MM'6" Lr:)N)typingrr thinc.apirrrrr r thinc.typesr compatr errorsrtokensr_precomputable_affiner tb_frameworkrboolintr7r0r/r1r?r@r:r6rms!JJ 7*LA 49d8n, -LA(LALA LA  LA  LA  LA LA^2;( D!r: