U 9%el=@sddlZddlZddlmZmZmZddlmZmZerFddl m Z er`ddl Z ddl mZGdd d ejZeeGd d d eZdS) N)add_end_docstringsis_tf_availableis_torch_available)PIPELINE_INIT_ARGSPipeline)!MODEL_FOR_CAUSAL_LM_MAPPING_NAMES)$TF_MODEL_FOR_CAUSAL_LM_MAPPING_NAMESc@seZdZdZdZdZdS) ReturnTyperrrN)__name__ __module__ __qualname__TENSORSNEW_TEXT FULL_TEXTrre/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/pipelines/text_generation.pyr sr c sheZdZdZdZfddZdddZfd d Zfd d ZdddZ ddZ e j dfddZ ZS)TextGenerationPipelinea- Language generation pipeline using any `ModelWithLMHead`. This pipeline predicts the words that will follow a specified text prompt. Example: ```python >>> from transformers import pipeline >>> generator = pipeline(model="gpt2") >>> generator("I can't believe you did such a ", do_sample=False) [{'generated_text': "I can't believe you did such a icky thing to me. I'm so sorry. I'm so sorry. I'm so sorry. I'm so sorry. I'm so sorry. I'm so sorry. I'm so sorry. I"}] >>> # These parameters will return suggestions, and only the newly created text making it easier for prompting suggestions. >>> outputs = generator("My tart needs some", num_return_sequences=4, return_full_text=False) ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial). You can pass text generation parameters to this pipeline to control stopping criteria, decoding strategy, and more. Learn more about text generation parameters in [Text generation strategies](../generation_strategies) and [Text generation](text_generation). This language generation pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"text-generation"`. The models that this pipeline can use are models that have been trained with an autoregressive language modeling objective, which includes the uni-directional models in the library (e.g. gpt2). See the list of available models on [huggingface.co/models](https://huggingface.co/models?filter=text-generation). a In 1991, the remains of Russian Tsar Nicholas II and his family (except for Alexei and Maria) are discovered. The voice of Nicholas's young son, Tsarevich Alexei Nikolaevich, narrates the remainder of the story. 1883 Western Siberia, a young Grigori Rasputin is asked by his father and a group of men to perform magic. Rasputin has a vision and denounces one of the men as a horse thief. Although his father initially slaps him for making such an accusation, Rasputin watches as the man is chased outside and beaten. Twenty years later, Rasputin sees a vision of the Virgin Mary, prompting him to become a priest. Rasputin quickly becomes famous, with people, even a bishop, begging for his blessing. cstj||||jdkr tntd|jkrd}|jjj dk rL|jjj }|dkrh|jj j dkrh|j }|dk r|j fd|i|j\}}}|j||_|j||_dS)Ntfprefix)ZXLNetLMHeadModelTransfoXLLMHeadModelZTFXLNetLMHeadModelZTFTransfoXLLMHeadModel)super__init__Zcheck_model_type frameworkr r Z_preprocess_paramsmodelconfigr __class__r XL_PREFIX_sanitize_parametersZ_forward_params)selfargskwargsrpreprocess_paramsforward_params_rrrrEs   zTextGenerationPipeline.__init__NFc KsJd| i} |dk r|| d<|rB|j|d| |jd} | djd| d<|dk rh|dkr`t|d || d <| | | } i}|dk r|dkr|dk rtd |dk rtd |rtjntj}|dk r|dkr|dk rtd tj}|dk r||d<|dk r||d<|dk r@|jj |dd}t |dkr4t d|d| d<| | |fS)Nadd_special_tokensrFpaddingr'return_tensors input_ids prefix_length>holezT is not a valid value for `handle_long_generation` parameter expected [None, 'hole']handle_long_generationz;`return_text` is mutually exclusive with `return_full_text`z>`return_full_text` is mutually exclusive with `return_tensors`z9`return_text` is mutually exclusive with `return_tensors` return_typeclean_up_tokenization_spaces)r'rzStopping on a multiple token sequence is not yet supported on transformers. The first token of the stop sequence will be used as the stop sequence string in the interim.rZ eos_token_id) tokenizerrshape ValueErrorupdater rrrencodelenwarningswarn)r Zreturn_full_textr*Z return_textr0r1rr/Z stop_sequencer'generate_kwargsr#Z prefix_inputsr$Zpostprocess_paramsZstop_sequence_idsrrrr`sT     z+TextGenerationPipeline._sanitize_parameterscs*|jjjdkr|dditj||S)z. Parse arguments and tokenize )rZadd_space_before_punct_symbolT)rrr r5r_parse_and_tokenize)r r!r"r&rrr;sz*TextGenerationPipeline._parse_and_tokenizec stj|f|S)a Complete the prompt(s) given as inputs. Args: args (`str` or `List[str]`): One or several prompts (or one list of prompts) to complete. return_tensors (`bool`, *optional*, defaults to `False`): Whether or not to return the tensors of predictions (as token indices) in the outputs. If set to `True`, the decoded text is not returned. return_text (`bool`, *optional*, defaults to `True`): Whether or not to return the decoded texts in the outputs. return_full_text (`bool`, *optional*, defaults to `True`): If set to `False` only added text is returned, otherwise the full text is returned. Only meaningful if *return_text* is set to True. clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`): Whether or not to clean up the potential extra spaces in the text output. prefix (`str`, *optional*): Prefix added to prompt. handle_long_generation (`str`, *optional*): By default, this pipelines does not handle long generation (ones that exceed in one form or the other the model maximum length). There is no perfect way to adress this (more info :https://github.com/huggingface/transformers/issues/14033#issuecomment-948385227). This provides common strategies to work around that problem depending on your use case. - `None` : default strategy where nothing in particular happens - `"hole"`: Truncates left of input, and leaves a gap wide enough to let generation happen (might truncate a lot of the prompt and not suitable when generation exceed the model capacity) generate_kwargs: Additional keyword arguments to pass along to the generate method of the model (see the generate method corresponding to your framework [here](./model#generative-models)). Return: A list or a list of list of `dict`: Returns one of the following dictionaries (cannot return a combination of both `generated_text` and `generated_token_ids`): - **generated_text** (`str`, present when `return_text=True`) -- The generated text. - **generated_token_ids** (`torch.Tensor` or `tf.Tensor`, present when `return_tensors=True`) -- The token ids of the generated text. )r__call__)r Z text_inputsr"r&rrr<s)zTextGenerationPipeline.__call__c Ks|j||d||jd}||d<|dkr|djd}d|krH|d}n&|d|jjj|}|d krntd |||jjkr|jj|} | d krtd |ddd| df|d<d |kr|d dd| df|d <|S) NFr( prompt_textr.r+r,max_new_tokens max_lengthrz0We cannot infer how many new tokens are expectedziWe cannot use `hole` to handle this generation the number of desired tokens exceeds the models max lengthattention_mask) r2rr3getrrr@r4Zmodel_max_length) r r>rr/r'r:inputscur_lenZ new_tokensZ keep_lengthrrr preprocesss0  z!TextGenerationPipeline.preprocessc Ksf|d}|dd}|jddkr0d}d}d}n |jd}|d}|dd}|dkrd|kptd|kot|djdk }|s|d p|jjj|d <|d |7<d |kpd|ko|djdk } | sd |kr|d |7<|jjf||d |} | jd} |j d kr,| j || |f| jdd} n.|j dkrZt | || |f| jdd} | ||dS)Nr+rArrr>r-r?Zgeneration_configr@min_new_tokensZ min_length)r+rAptr)generated_sequencer+r>) rBr3popr?rrr@rFgeneraterZreshaper) r Z model_inputsr:r+rAZin_br>r-Zhas_max_new_tokensZhas_min_new_tokensrHZout_brrr_forwards<         " "zTextGenerationPipeline._forwardTc Cs|dd}|d}|d}|}g}|D]}|tjkrHd|i} np|tjtjhkr|jj|d|d} |dkrxd} nt|jj|dd|d} | | d} |tjkr|| } d| i} | | q0|S) NrHrr+r>Zgenerated_token_idsT)Zskip_special_tokensr1Zgenerated_text) numpytolistr rrrr2decoder7append) r Z model_outputsr0r1rHr+r>recordssequencerecordtextZ prompt_lengthZall_textrrr postprocesss:       z"TextGenerationPipeline.postprocess) NNNNNNNNF)r=NF)r r r__doc__rrrr;r<rErKr rrT __classcell__rrr&rrs*"  = , 'r)enumr8utilsrrrbaserrZmodels.auto.modeling_autor Z tensorflowrZmodels.auto.modeling_tf_autor Enumr rrrrrs