a  d.@s~ddlmZmZddlZddlmZddlmZm Z ddl m Z m Z m Z e eZGdd d e Zee Gd d d e ZdS) )ListUnionN)TruncationStrategy)add_end_docstringslogging)PIPELINE_INIT_ARGSArgumentHandler ChunkPipelinec@s eZdZdZddZddZdS)%ZeroShotClassificationArgumentHandlerz Handles arguments for zero-shot for text classification by turning each possible label into an NLI premise/hypothesis pair. cCs"t|trdd|dD}|S)NcSsg|]}|r|qS)strip.0labelr r x/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/transformers/pipelines/zero_shot_classification.py zGZeroShotClassificationArgumentHandler._parse_labels..,) isinstancestrsplit)selflabelsr r r _parse_labelss z3ZeroShotClassificationArgumentHandler._parse_labelscst|dkst|dkr td|dkr@tdt|trP|g}g}|D]|fdd|DqX||fS)Nrz>You must include at least one label and at least one sequence.zThe provided hypothesis_template "{}" 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.csg|]}|gqSr )formatrhypothesis_templatesequencer rr(rzBZeroShotClassificationArgumentHandler.__call__..)len ValueErrorrrrextend)r sequencesrrsequence_pairsr rr__call__s z.ZeroShotClassificationArgumentHandler.__call__N)__name__ __module__ __qualname____doc__rr%r r r rr sr cseZdZdZeffdd ZeddZddej fddZ d d Z e e ee fd fd d ZdddZddZdddZZS)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). cs0||_tj|i||jdkr,tddS)NzFailed 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.) _args_parsersuper__init__ entailment_idloggerwarning)rZ args_parserargskwargs __class__r rr.Vs  z'ZeroShotClassificationPipeline.__init__cCs2|jjjD]\}}|dr|SqdS)NZentailr+)modelconfigZlabel2iditemslower startswith)rrindr r rr/_s z,ZeroShotClassificationPipeline.entailment_idTc Ks|j}|jjdur(td|jj|j_z|j|||||d}WnLty}z4dt|vrt|j||||tj d}n|WYd}~n d}~00|S)ze Parse arguments and tokenize only_first so that hypothesis (label) is not truncated NzfTokenizer was not supporting padding necessary for zero-shot, attempting to use `pad_token=eos_token`)add_special_tokensreturn_tensorspadding truncationz too short) Z framework tokenizerZ pad_tokenr0errorZ eos_token ExceptionrrZDO_NOT_TRUNCATE) rr$r>r<r?r3r=inputser r r_parse_and_tokenizefs2    z2ZeroShotClassificationPipeline._parse_and_tokenizecKs||dddur&|d|d<tdi}d|vrF|j|d|d<d|vrZ|d|d<i}d|vrr|d|d<|i|fS)NZ multi_class multi_labelzThe `multi_class` argument has been deprecated and renamed to `multi_label`. `multi_class` will be removed in a future version of Transformers.candidate_labelsr)getr0r1r,r)rr3Zpreprocess_paramsZpostprocess_paramsr r r_sanitize_parameterss   z3ZeroShotClassificationPipeline._sanitize_parameters)r#csRt|dkrn0t|dkr0d|vr0|d|d<ntd|tj|fi|S)a 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. rrrGz%Unable to understand extra arguments )r r!r-r%)rr#r2r3r4r rr%s $ z'ZeroShotClassificationPipeline.__call__NThis example is {}.c cs`||||\}}tt||D]:\}\}}||g} ||d|t|dkd| Vq dS)Nrrcandidate_labelris_last)r, enumerateziprEr ) rrCrGrr$r#irLZ sequence_pairZ model_inputr r r preprocesss z)ZeroShotClassificationPipeline.preprocesscsNd}d}fdd|jjD}|jfi|}||dd|}|S)NrLrcsi|]}||qSr r )rkrCr r rz;ZeroShotClassificationPipeline._forward..rMrK)r@Zmodel_input_namesr6)rrCrLrZ model_inputsoutputs model_outputsr rSr_forwardsz'ZeroShotClassificationPipeline._forwardFcs"dd|Ddd|D}tdd|D}|jd}t}||}|||df}|sjtdkr|j} | dkr|dnd} |d| | gf} t| t| jdd d } | d } n,|d|jf} t| t| jdd d } tt | d }|dfd d|D| d|f d S)NcSsg|] }|dqS)rLr rrUr r rrrz>ZeroShotClassificationPipeline.postprocess..cSsg|] }|dqS)rr rXr r rrrcSsg|]}|dqS)logits)numpy)routputr r rrrrr+r.T)Zkeepdims).rcsg|] }|qSr r )rrPrGr rrr)rrscores) npZ concatenateshaper Zreshaper/expsumlistreversedZargsorttolist)rrVrFr#rYNnZ num_sequencesZreshaped_outputsr/Zcontradiction_idZentail_contr_logitsr]Z entail_logitsZtop_indsr r\r postprocesss(  z*ZeroShotClassificationPipeline.postprocess)NrJ)F)r&r'r(r)r r.propertyr/rZ ONLY_FIRSTrErIrrrr%rQrWrg __classcell__r r r4rr*-s'   *- r*)typingrrrZr^Ztokenization_utilsrutilsrrbaser r r Z get_loggerr&r0r r*r r r rs