+ j.^RIt^RIt^RIHt^RIHtHt^RIH t H t H t ]P!] 4t!RR] 4t]!] !RR74!R R ] 44tR#) N)TruncationStrategy)add_end_docstringslogging)ArgumentHandler ChunkPipelinebuild_pipeline_init_argsc0a]tRt^ toRtRtRtRtVtR#)%ZeroShotClassificationArgumentHandlerz} Handles arguments for zero-shot for text classification by turning each possible label into an NLI premise/hypothesis pair. c\V\4'dFVPR4Uu.uF*q"P4'gKVP4NK, ppV#uupi),) isinstancestrsplitstrip)selflabelslabels&& p/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/pipelines/zero_shot_classification.py _parse_labels3ZeroShotClassificationArgumentHandler._parse_labelssG fc " "17c1BT1Bkkmmekkm1BFT Us AAc j\V4^8Xg\V4^8Xd \R4hVPV^,4V8Xd\RV R24h\V\4'dV.p.pVF4pTP VUu.uFqeVPV4.NK up4K6 WA3#uupi)rz>You must include at least one label and at least one sequence.z"The provided hypothesis_template "z" was not able to be formatted with the target labels. Make sure the passed template includes formatting syntax such as {} where the label should go.)len ValueErrorformatr rextend)r sequencesrhypothesis_templatesequence_pairssequencers&&&& r__call__.ZeroShotClassificationArgumentHandler.__call__s v;! s9~2]^ ^  % %fQi 04G G45H4IJqq  i % %" I!H  ! !^d"e^dUZ.A.H.H.O#P^d"e f"((#fsB0 N) __name__ __module__ __qualname____firstlineno____doc__rr __static_attributes____classdictcell__) __classdict__s@rr r s  ))r T) has_tokenizercaa]tRt^+toRtRtRtRtRt] !43V3Rllt ] R4t RR] P3RltRtV3RlV3R lltRR ltR tRR ltR tVtV;t#)ZeroShotClassificationPipelinea NLI-based zero-shot classification pipeline using a `ModelForSequenceClassification` trained on NLI (natural language inference) tasks. Equivalent of `text-classification` pipelines, but these models don't require a hardcoded number of potential classes, they can be chosen at runtime. It usually means it's slower but it is **much** more flexible. Any combination of sequences and labels can be passed and each combination will be posed as a premise/hypothesis pair and passed to the pretrained model. Then, the logit for *entailment* is taken as the logit for the candidate label being valid. Any NLI model can be used, but the id of the *entailment* label must be included in the model config's :attr:*~transformers.PreTrainedConfig.label2id*. Example: ```python >>> from transformers import pipeline >>> oracle = pipeline(model="facebook/bart-large-mnli") >>> oracle( ... "I have a problem with my iphone that needs to be resolved asap!!", ... candidate_labels=["urgent", "not urgent", "phone", "tablet", "computer"], ... ) {'sequence': 'I have a problem with my iphone that needs to be resolved asap!!', 'labels': ['urgent', 'phone', 'computer', 'not urgent', 'tablet'], 'scores': [0.504, 0.479, 0.013, 0.003, 0.002]} >>> oracle( ... "I have a problem with my iphone that needs to be resolved asap!!", ... candidate_labels=["english", "german"], ... ) {'sequence': 'I have a problem with my iphone that needs to be resolved asap!!', 'labels': ['english', 'german'], 'scores': [0.814, 0.186]} ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This NLI pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"zero-shot-classification"`. The models that this pipeline can use are models that have been fine-tuned on an NLI task. See the up-to-date list of available models on [huggingface.co/models](https://huggingface.co/models?search=nli). FTc <Wn\SV`!R/VBVPR8Xd\P R4R#R#)zFailed to determine 'entailment' label id from the label2id mapping in the model config. Setting to -1. Define a descriptive label2id mapping in the model config to ensure correct outputs.Nr") _args_parsersuper__init__ entailment_idloggerwarning)r args_parserkwargs __class__s&&,rr4'ZeroShotClassificationPipeline.__init__Ys>' "6"    # NNk  $r+cVPPPP4F.wrVP 4P R4'gK,Vu# R#)entailr1)modelconfiglabel2iditemslower startswith)rrinds& rr5,ZeroShotClassificationPipeline.entailment_idbsJ**++44::> # # + LL) (,~~'?'?DNN $ ^^#5-% $F2 % c!f$"'9#1#1AA ( ! sA.. B:94B53B55B:c /pRV9d&VPPVR,4VR&RV9d VR,VR&/pRV9d VR,VR&V/V3#)candidate_labelsr multi_label)r2r)rr9preprocess_paramspostprocess_paramss&, r_sanitize_parameters3ZeroShotClassificationPipeline._sanitize_parameterssz  '484E4E4S4STZ[mTn4o 0 1 F *7=>S7T 3 4 F "06}0E } - "&888r+c@<V^8dQhRS[S[S[,,/#)r)rlist)rr*s"r __annotate__+ZeroShotClassificationPipeline.__annotate__s+5+5c?+5r+c <\V4^8XdM2\V4^8XdRV9dV^,VR&M\RV 24h\SV` !V3/VB#)aJ Classify the sequence(s) given as inputs. See the [`ZeroShotClassificationPipeline`] documentation for more information. Args: sequences (`str` or `list[str]`): The sequence(s) to classify, will be truncated if the model input is too large. candidate_labels (`str` or `list[str]`): The set of possible class labels to classify each sequence into. Can be a single label, a string of comma-separated labels, or a list of labels. hypothesis_template (`str`, *optional*, defaults to `"This example is {}."`): The template used to turn each label into an NLI-style hypothesis. This template must include a {} or similar syntax for the candidate label to be inserted into the template. For example, the default template is `"This example is {}."` With the candidate label `"sports"`, this would be fed into the model like `" sequence to classify This example is sports . "`. The default template works well in many cases, but it may be worthwhile to experiment with different templates depending on the task setting. multi_label (`bool`, *optional*, defaults to `False`): Whether or not multiple candidate labels can be true. If `False`, the scores are normalized such that the sum of the label likelihoods for each sequence is 1. If `True`, the labels are considered independent and probabilities are normalized for each candidate by doing a softmax of the entailment score vs. the contradiction score. Return: A `dict` or a list of `dict`: Each result comes as a dictionary with the following keys: - **sequence** (`str`) -- The sequence for which this is the output. - **labels** (`list[str]`) -- The labels sorted by order of likelihood. - **scores** (`list[float]`) -- The probabilities for each of the labels. rWz%Unable to understand extra arguments )rrr3r )rrargsr9r:s&&*,rr 'ZeroShotClassificationPipeline.__call__s^H t9>  Y!^ 2& @)-aF% &DTFKL Lw 4V44r+c #"VPWV4wrE\\W$44F@wpwrxVPV.4p RVRV^,RV\ V4^, 8H/V CxKB R#5i)candidate_labelris_lastN)r2 enumerateziprTr) rrRrWrrrirf sequence_pair model_inputs &&&& r preprocess)ZeroShotClassificationPipeline.preprocesss$($5$5fPc$d!3forwardinspect signature parameters) rrRrfrk model_inputs model_forwardoutputs model_outputss && r_forward'ZeroShotClassificationPipeline._forwards !23*%.2nn.N.NO.N69 .N O ** '++M:EE E(-L %**,|,   vi(   PsB#cVUu.uF q3R,NK ppVUu.uF q3R,NK pp\P!VUu.uF'qfR,P4P4NK) up4pVP^,p\ V4p W,p VP WR34p V'g\ V4^8XdpVPp V ^8XdRM^p V RW.3,p\P!V4\P!V4PRRR7, pVR ,pMWV RVP3,p\P!V4\P!V4PRRR7, p\\V^,P444pRV^,RVUu.uF pVV,NK upRV^V3,P4/#uupiuupiuupiuupi) rfrlogits.T)keepdimsrscoresr1).r0)np concatenatefloatnumpyshaperreshaper5expsumr_reversedargsorttolist)rrzrXryrWroutputr~Nn num_sequencesreshaped_outputsr5contradiction_identail_contr_logitsr entail_logitstop_indsrjs&&& r postprocess*ZeroShotClassificationPipeline.postprocesssFSTm7$566mT8EF WZ(( FP] ^P]f!1!7!7!9!?!?!AP] ^_ LLO  ! !>>=R*@A #./14 ..M%2a%7rQ "239I8Y3Y"Z VV/0266:M3N3R3RSU`d3R3eeFF^F-S$2D2D-DEMVVM*RVVM-B-F-FrTX-F-YYF!2!2!456  ! H=Hq'**H= fQ[)002  +UF ^*>sG4G9-G>H )r2)NzThis example is {}.)F)r#r$r%r&r'_load_processor_load_image_processor_load_feature_extractor_load_tokenizerr r4propertyr5r ONLY_FIRSTrTr[r rmr{rr(r) __classcell__)r:r*s@@rr.r.+s|%NO!#O#H#J'+tPbPmPm(T 9+5+5Z $  r+r.)rsrrtokenization_pythonrutilsrrbaserrr get_loggerr#r6r r.r"r+rrs_4/JJ   H %)O)<,4@AY ]Y BY r+