g!.ddlZddlZddlZddlmZddlmZmZmZm Z m Z m Z m Z ddl mZddlmZddlmZddlmZdd lmZdd lmZdd lmZmZdd lmZmZdd lm Z m!Z!ddl"m#Z#m$Z$ddl%m&Z&m'Z'ddl(m)Z)ddl*m+Z+ddl,m-Z-m.Z.m/Z/m0Z0m1Z1m2Z2m3Z3m4Z4m5Z5m6Z6m7Z7m8Z8ddl9m:Z:ddl;mZ>m?Z?m@Z@mAZAmBZBmCZCmDZDmEZEmFZFmGZGddlHmIZIddlJmKZKddlLmMZMddlNmOZOddlPmQZQddlRmSZSddlTmUZUddlVmWZWddlXmYZYdd lZm[Z[dd!l\m]Z]dd"l^m_Z_m`Z`dd#lambZbmcZcdd$ldmeZemfZfmgZgdd%lhmiZidd&ljmkZkdd'llmmZmdd(lnmoZompZpmqZqmrZrdd)lsmtZtdd*lumvZvdd+lwmxZxdd,lymzZzm{Z{dd-l|m}Z}dd.l~mZe6rddlZdd/lmZmZmZmZmZmZmZmZmZmZmZe7r8ddlZdd0lmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZerdd1lmZdd2lmZdd3lmZe8jeZd4d5d6d7d8Zid9e:d:e7refnd:d;dd?d@err>rzSUPPORTED_TASK z contains invalid type )supported_tasks task_aliasesreturnc4tS)z3 Returns a list of supported task strings. )PIPELINE_REGISTRYget_supported_tasksr[/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/pipelines/__init__.pyrrs  0 0 2 22rtokenc |dd}|-tjdt|t d|}t rt d t||}n$#t$r}t d|d}~wwxYw|j st d|dt|d d d krt d |j d |j }|S) Nuse_auth_tokenrThe `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.V`token` and `use_auth_token` are both specified. Please set only the argument `token`.zMYou cannot infer task automatically within `pipeline` when using offline mode)rz=Instantiating a pipeline without a task set raised an error: z The model zS does not seem to have a correct `pipeline_tag` set to infer the task automatically library_name transformersz$This model is meant to be used with z not with transformers) popwarningswarn FutureWarning ValueErrorr$ RuntimeErrorr Exception pipeline_taggetattrr)rrdeprecated_kwargsrinfoetasks rget_taskrs8&**+;TBBN!  A      uvv vljkkk`%u--- ```^[\^^___`    s s s s   t^^44FFk$BSkkklll  D Ks$A66 BBBrc6t|S)a Checks an incoming task string, to validate it's correct and return the default Pipeline and Model classes, and default models if they exist. Args: task (`str`): The task defining which pipeline will be returned. Currently accepted tasks are: - `"audio-classification"` - `"automatic-speech-recognition"` - `"conversational"` - `"depth-estimation"` - `"document-question-answering"` - `"feature-extraction"` - `"fill-mask"` - `"image-classification"` - `"image-feature-extraction"` - `"image-segmentation"` - `"image-to-text"` - `"image-to-image"` - `"object-detection"` - `"question-answering"` - `"summarization"` - `"table-question-answering"` - `"text2text-generation"` - `"text-classification"` (alias `"sentiment-analysis"` available) - `"text-generation"` - `"text-to-audio"` (alias `"text-to-speech"` available) - `"token-classification"` (alias `"ner"` available) - `"translation"` - `"translation_xx_to_yy"` - `"video-classification"` - `"visual-question-answering"` (alias `"vqa"` available) - `"zero-shot-classification"` - `"zero-shot-image-classification"` - `"zero-shot-object-detection"` Returns: (normalized_task: `str`, task_defaults: `dict`, task_options: (`tuple`, None)) The normalized task name (removed alias and options). The actual dictionary required to initialize the pipeline and some extra task options for parametrized tasks like "translation_XX_to_YY" )r check_task)rs rrrsZ  ' ' - --rcjddld|vrtd|dd}t|tr|g}t fd|D|d<|dd}t|tr|g}t fd|D|d<|dfS) NrrzNThis model introduces a custom pipeline without specifying its implementation.rrc38K|]}t|VdSNr.0crs r z$clean_custom_task.."-MMGL!44MMMMMMrrc38K|]}t|VdSrrrs rrz$clean_custom_task..&rr)rrget isinstancestrtuple) task_infopt_class_namestf_class_namesrs @rclean_custom_taskrs Yklll]]4,,N.#&&*()MMMMnMMMMMIdO]]4,,N.#&&*()MMMMnMMMMMIdO d?rTr{rzr tokenizerr|feature_extractorimage_processor processor frameworkrevisionuse_fastdevicez torch.devicetrust_remote_code model_kwargspipeline_classc |i}|dd}|-tjdt| t d|} |dd}|dd}|| ||d}||t d||t d ||t d t |trt|}|d}t |tr|}n|t |tr|}t |tsA|?t|tfd d d | d d |}t|||d<nt|dd|d<t |tr"tj|f||d||}|j|d<n|t |trt%rd|D}t)||d|d|d}|Ft+|dd5}t-j|}|d}dddn #1swxYwYtj|f||d||}|j|d<i}|t1t|didkr|j}|v|d urrt1|dkr(t5|d}n7t dd||:|8t |tst d|dt;|| }||vrF|}t=||\}}|)|st d|d} t?| |fd|i|}ntA|\}}}||d}|tC|||\}}!||n|!}tD#d |d!|d"tHd#|d$ ||d<|5t |tr tj|fd%|i||}|j|d<| 4d&|vrt d'| tD#d(| |d&<| Wd)|vrt d*t | tr*tKtL| rttL| } | |d)<t |tr|nd}"t |ts|(|d+|d,d-}#tO|f|#|||d.||\}}|j(}$|j(j|d<tS|$tTvp|$j+du}%tS|$tXvp|du}&tS|$tZvp|du}'tS|$t\vp|du}(|%o|j/}%|&o|j0}&|'o|j1}'|(o|j2}(|'r|&rd }&|3|%s1|tfvr(|$j4j5tlvs|$j4j5tnvrd/}%| |'s|tpvr|$j4j5tnvrd/}'| |&s|trvr|$j4j5tlvrd/}&|tfvrd }%|trvrd }&|tpvrd }'|%r|?t |"tr|"}n't |tr|}ntud0t |ttvfrt |tvr-|dd1| } |d})|d}*n,|})|<}*|*d)dt{j|)f| |d2||*}|'r|Yt |"tr|"}nAt |tr|}n)|t |t|r|}ntud3t |ttvfrtj|fd%|i||}|&r|?t |"tr|"}n't |tr|}ntud4t |ttvfrtj|fd%|i||}|jArd|jABd5rIt |"tr3 ddlC}+dd6lDmE},tjGH|"stjGI|"r|,J|"}-nGtjG|,jKd7}.|,jL}/|.|/g}0|,M|"|08}-|-|d9<n#t$rz}1tD#d:|"d;|1tstD#d<tstD#d=Yd}1~1nd}1~1wwxYw|(r|?t |"tr|"}n't |tr|}ntud>t |ttvfrKtj|fd%|i||}t |ts td?tS|d@|dAkrR|j(jTrF|j(jTD]9}2|2UdAr"|2}tjdB|dCtn:|||dD<|||dE<| | |d)<|||dF<| | |dG<|||dH<|dJ|||dI|S)KaD- Utility factory method to build a [`Pipeline`]. A pipeline consists of: - One or more components for pre-processing model inputs, such as a [tokenizer](tokenizer), [image_processor](image_processor), [feature_extractor](feature_extractor), or [processor](processors). - A [model](model) that generates predictions from the inputs. - Optional post-processing steps to refine the model's output, which can also be handled by processors. While there are such optional arguments as `tokenizer`, `feature_extractor`, `image_processor`, and `processor`, they shouldn't be specified all at once. If these components are not provided, `pipeline` will try to load required ones automatically. In case you want to provide these components explicitly, please refer to a specific pipeline in order to get more details regarding what components are required. Args: task (`str`): The task defining which pipeline will be returned. Currently accepted tasks are: - `"audio-classification"`: will return a [`AudioClassificationPipeline`]. - `"automatic-speech-recognition"`: will return a [`AutomaticSpeechRecognitionPipeline`]. - `"depth-estimation"`: will return a [`DepthEstimationPipeline`]. - `"document-question-answering"`: will return a [`DocumentQuestionAnsweringPipeline`]. - `"feature-extraction"`: will return a [`FeatureExtractionPipeline`]. - `"fill-mask"`: will return a [`FillMaskPipeline`]:. - `"image-classification"`: will return a [`ImageClassificationPipeline`]. - `"image-feature-extraction"`: will return an [`ImageFeatureExtractionPipeline`]. - `"image-segmentation"`: will return a [`ImageSegmentationPipeline`]. - `"image-to-image"`: will return a [`ImageToImagePipeline`]. - `"image-to-text"`: will return a [`ImageToTextPipeline`]. - `"mask-generation"`: will return a [`MaskGenerationPipeline`]. - `"object-detection"`: will return a [`ObjectDetectionPipeline`]. - `"question-answering"`: will return a [`QuestionAnsweringPipeline`]. - `"summarization"`: will return a [`SummarizationPipeline`]. - `"table-question-answering"`: will return a [`TableQuestionAnsweringPipeline`]. - `"text2text-generation"`: will return a [`Text2TextGenerationPipeline`]. - `"text-classification"` (alias `"sentiment-analysis"` available): will return a [`TextClassificationPipeline`]. - `"text-generation"`: will return a [`TextGenerationPipeline`]:. - `"text-to-audio"` (alias `"text-to-speech"` available): will return a [`TextToAudioPipeline`]:. - `"token-classification"` (alias `"ner"` available): will return a [`TokenClassificationPipeline`]. - `"translation"`: will return a [`TranslationPipeline`]. - `"translation_xx_to_yy"`: will return a [`TranslationPipeline`]. - `"video-classification"`: will return a [`VideoClassificationPipeline`]. - `"visual-question-answering"`: will return a [`VisualQuestionAnsweringPipeline`]. - `"zero-shot-classification"`: will return a [`ZeroShotClassificationPipeline`]. - `"zero-shot-image-classification"`: will return a [`ZeroShotImageClassificationPipeline`]. - `"zero-shot-audio-classification"`: will return a [`ZeroShotAudioClassificationPipeline`]. - `"zero-shot-object-detection"`: will return a [`ZeroShotObjectDetectionPipeline`]. model (`str` or [`PreTrainedModel`] or [`TFPreTrainedModel`], *optional*): The model that will be used by the pipeline to make predictions. This can be a model identifier or an actual instance of a pretrained model inheriting from [`PreTrainedModel`] (for PyTorch) or [`TFPreTrainedModel`] (for TensorFlow). If not provided, the default for the `task` will be loaded. config (`str` or [`PretrainedConfig`], *optional*): The configuration that will be used by the pipeline to instantiate the model. This can be a model identifier or an actual pretrained model configuration inheriting from [`PretrainedConfig`]. If not provided, the default configuration file for the requested model will be used. That means that if `model` is given, its default configuration will be used. However, if `model` is not supplied, this `task`'s default model's config is used instead. tokenizer (`str` or [`PreTrainedTokenizer`], *optional*): The tokenizer that will be used by the pipeline to encode data for the model. This can be a model identifier or an actual pretrained tokenizer inheriting from [`PreTrainedTokenizer`]. If not provided, the default tokenizer for the given `model` will be loaded (if it is a string). If `model` is not specified or not a string, then the default tokenizer for `config` is loaded (if it is a string). However, if `config` is also not given or not a string, then the default tokenizer for the given `task` will be loaded. feature_extractor (`str` or [`PreTrainedFeatureExtractor`], *optional*): The feature extractor that will be used by the pipeline to encode data for the model. This can be a model identifier or an actual pretrained feature extractor inheriting from [`PreTrainedFeatureExtractor`]. Feature extractors are used for non-NLP models, such as Speech or Vision models as well as multi-modal models. Multi-modal models will also require a tokenizer to be passed. If not provided, the default feature extractor for the given `model` will be loaded (if it is a string). If `model` is not specified or not a string, then the default feature extractor for `config` is loaded (if it is a string). However, if `config` is also not given or not a string, then the default feature extractor for the given `task` will be loaded. image_processor (`str` or [`BaseImageProcessor`], *optional*): The image processor that will be used by the pipeline to preprocess images for the model. This can be a model identifier or an actual image processor inheriting from [`BaseImageProcessor`]. Image processors are used for Vision models and multi-modal models that require image inputs. Multi-modal models will also require a tokenizer to be passed. If not provided, the default image processor for the given `model` will be loaded (if it is a string). If `model` is not specified or not a string, then the default image processor for `config` is loaded (if it is a string). processor (`str` or [`ProcessorMixin`], *optional*): The processor that will be used by the pipeline to preprocess data for the model. This can be a model identifier or an actual processor inheriting from [`ProcessorMixin`]. Processors are used for multi-modal models that require multi-modal inputs, for example, a model that requires both text and image inputs. If not provided, the default processor for the given `model` will be loaded (if it is a string). If `model` is not specified or not a string, then the default processor for `config` is loaded (if it is a string). framework (`str`, *optional*): The framework to use, either `"pt"` for PyTorch or `"tf"` for TensorFlow. The specified framework must be installed. If no framework is specified, will default to the one currently installed. If no framework is specified and both frameworks are installed, will default to the framework of the `model`, or to PyTorch if no model is provided. revision (`str`, *optional*, defaults to `"main"`): When passing a task name or a string model identifier: The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any identifier allowed by git. use_fast (`bool`, *optional*, defaults to `True`): Whether or not to use a Fast tokenizer if possible (a [`PreTrainedTokenizerFast`]). use_auth_token (`str` or *bool*, *optional*): The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated when running `huggingface-cli login` (stored in `~/.huggingface`). device (`int` or `str` or `torch.device`): Defines the device (*e.g.*, `"cpu"`, `"cuda:1"`, `"mps"`, or a GPU ordinal rank like `1`) on which this pipeline will be allocated. device_map (`str` or `Dict[str, Union[int, str, torch.device]`, *optional*): Sent directly as `model_kwargs` (just a simpler shortcut). When `accelerate` library is present, set `device_map="auto"` to compute the most optimized `device_map` automatically (see [here](https://huggingface.co/docs/accelerate/main/en/package_reference/big_modeling#accelerate.cpu_offload) for more information). Do not use `device_map` AND `device` at the same time as they will conflict torch_dtype (`str` or `torch.dtype`, *optional*): Sent directly as `model_kwargs` (just a simpler shortcut) to use the available precision for this model (`torch.float16`, `torch.bfloat16`, ... or `"auto"`). trust_remote_code (`bool`, *optional*, defaults to `False`): Whether or not to allow for custom code defined on the Hub in their own modeling, configuration, tokenization or even pipeline files. This option should only be set to `True` for repositories you trust and in which you have read the code, as it will execute code present on the Hub on your local machine. model_kwargs (`Dict[str, Any]`, *optional*): Additional dictionary of keyword arguments passed along to the model's `from_pretrained(..., **model_kwargs)` function. kwargs (`Dict[str, Any]`, *optional*): Additional keyword arguments passed along to the specific pipeline init (see the documentation for the corresponding pipeline class for possible values). Returns: [`Pipeline`]: A suitable pipeline for the task. Examples: ```python >>> from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer >>> # Sentiment analysis pipeline >>> analyzer = pipeline("sentiment-analysis") >>> # Question answering pipeline, specifying the checkpoint identifier >>> oracle = pipeline( ... "question-answering", model="distilbert/distilbert-base-cased-distilled-squad", tokenizer="google-bert/bert-base-cased" ... ) >>> # Named entity recognition pipeline, passing in a specific model and tokenizer >>> model = AutoModelForTokenClassification.from_pretrained("dbmdz/bert-large-cased-finetuned-conll03-english") >>> tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-cased") >>> recognizer = pipeline("ner", model=model, tokenizer=tokenizer) ```Nrrr code_revision _commit_hash)rrrrz}Impossible to instantiate a pipeline without either a task or a model being specified. Please provide a task class or a modelaImpossible to instantiate a pipeline with tokenizer specified but not the model as the provided tokenizer may not be compatible with the default model. Please provide a PreTrainedModel class or a path/identifier to a pretrained model when providing tokenizer.aImpossible to instantiate a pipeline with feature_extractor specified but not the model as the provided feature_extractor may not be compatible with the default model. Please provide a PreTrainedModel class or a path/identifier to a pretrained model when providing feature_extractor.F cache_dir) _raise_exceptions_for_gated_repo%_raise_exceptions_for_missing_entries'_raise_exceptions_for_connection_errorsr)_from_pipelinerc&i|]\}}|dk ||S)rr)rkvs r zpipeline..6s)[[[DAq!GZBZBZ1aBZBZBZrrr)rrrrzutf-8)encodingbase_model_name_or_pathcustom_pipelinesrr*zhWe can't infer the task automatically for this model as there are multiple tasks available. Pick one in z, z_Inferring the task automatically requires to check the hub with a model_id defined as a `str`. z is not a valid model_id.zLoading this pipeline requires you to execute the code in the pipeline file in that repo on your local machine. Make sure you have read the code there to avoid malicious use, then set the option `trust_remote_code=True` to remove this error.rz$No model was supplied, defaulted to z and revision z (/zb). Using a pipeline without specifying a model name and revision in production is not recommended.r device_mapzYou cannot use both `pipeline(... device_map=..., model_kwargs={"device_map":...})` as those arguments might conflict, use only one.)zBoth `device` and `device_map` are specified. `device` will override `device_map`. You will most likely encounter unexpected behavior. Please remove `device` and keep `device_map`. torch_dtypezYou cannot use both `pipeline(... torch_dtype=..., model_kwargs={"torch_dtype":...})` as those arguments might conflict, use only one.)rr)rr) model_classesrrrTzImpossible to guess which tokenizer to use. Please provide a PreTrainedTokenizer class or a path/identifier to a pretrained tokenizer.r)rrzImpossible to guess which image processor to use. Please provide a PreTrainedImageProcessor class or a path/identifier to a pretrained image processor.zImpossible to guess which feature extractor to use. Please provide a PreTrainedFeatureExtractor class or a path/identifier to a pretrained feature extractor.WithLM)BeamSearchDecoderCTC*)allow_patternsdecoderz!Could not load the `decoder` for z . Defaulting to raw CTC. Error: z*Try to install `kenlm`: `pip install kenlmz6Try to install `pyctcdecode`: `pip install pyctcdecodeztImpossible to guess which processor to use. Please provide a processor instance or a path/identifier to a processor.zOProcessor was loaded, but it is not an instance of `ProcessorMixin`. Got type `z}` instead. Please check that you specified correct pipeline task for the model and model has processor implemented and saved.rzO"translation" task was used, instead of "translation_XX_to_YY", defaulting to ""rrrrr)rrrr)Wrrrrrrrrrr r rrr!rrfrom_pretrainedrr%itemsr"openjsonloadlenrlistkeysjoinrrrrr5loggerwarningrhasattrtorchr6rrrtokenizer_classrrr_load_tokenizer_load_feature_extractor_load_image_processor_load_processorNO_TOKENIZER_TASKS __class____name__MULTI_MODEL_AUDIO_CONFIGSMULTI_MODEL_VISION_CONFIGSNO_IMAGE_PROCESSOR_TASKSNO_FEATURE_EXTRACTOR_TASKSrrcopyrrrr_processor_classendswithkenlm pyctcdecoderospathisdirisfile load_from_dir$_LANGUAGE_MODEL_SERIALIZED_DIRECTORY_ALPHABET_SERIALIZED_FILENAMEload_from_hf_hub ImportErrorr#r&rr TypeErrortask_specific_params startswith UserWarning)3rrrrrrrrrrrrrrrrrkwargsrr commit_hash hub_kwargspretrained_model_name_or_pathresolved_config_file _hub_kwargsmaybe_adapter_pathfadapter_config custom_tasksnormalized_task targeted_task task_options class_refdefault_revision model_namer model_configload_tokenizerload_feature_extractorload_image_processorload_processortokenizer_identifiertokenizer_kwargsr#rrlanguage_model_globalphabet_filenamerrkeys3 rpipelinerL*s>z "%%&6==N!  A      uvv vJJ55M**^T22K.# J |  5    }. O    }*6 \   %E (,% fc " " 2,2 ) ) ^ 5# 6 6^,1 )&"233 O8U8a#.-$276;8=&**;77 $$$$ *==QS^)_)_J~ & &)0)N)NJ~ &&#9+  #'}  HR Vb  &,%8 >"" Juc22    F[[J,<,<,>,>[[[K!9 )#J/'7 """ "-,cGDDDF%)Yq\\N*+DEEFFFFFFFFFFFFFFF+  "&m  GQ Ua  &,%8 >"L c'&2Db"I"IJJQNN. <-U::<  A%%L--//003"?"ii (9(9(;(;<<??  |)%%% 4444 u%% |&7 T8J&K&K# |  !$  U &f-I:, N8B$7G7G4  !*62N }"@PY[g"h"h'3889I n5 n n n n; n n>C n n n   "* : >j44>/iidiji\hiiF)/)OQc3d3d."3 7 oU| 4 4 0@048BFRO/a  $*c** $.!!FC(( $*!! 9 '#u 6 6 a 4 D!!!26!:D!HT!!  "2 a%6??II az3// a a LLL@@@@@@w}}Z00sBGNN:4N4Ns"6"D"DZ"P"P.0gll0UWZ//+-A,^)*=?P)Q"6"G"G cq"G"r"r(/F9%%"aaaNN#vz#v#vst#v#vwww-//U'STTT355a'_``` a  *c** & FC(( "  & i#u . . %5issPTsXbsfrssIi88 i!%iiii  }!B<4  C~~m,,  mfjmmm  '{$&7"# +}"$3 ! !x'{ > P P P P PPs,,IIIB*e gA0g  gr)NNNNNNNNNTNNNNNNN)r r%rpathlibrtypingrrrrrr r huggingface_hubr configuration_utilsr dynamic_module_utilsrfeature_extraction_utilsrimage_processing_utilsrmodels.auto.configuration_autor#models.auto.feature_extraction_autorr!models.auto.image_processing_autorrmodels.auto.modeling_autorrmodels.auto.processing_autorrmodels.auto.tokenization_autorrprocessing_utilsrtokenization_utilsrutilsrrr r!r"r#r$r%r&r'r(r)audio_classificationr+automatic_speech_recognitionr,baser-r.r/r0r1r2r3r4r5r6depth_estimationr7document_question_answeringr8feature_extractionr9 fill_maskr:image_classificationr;image_feature_extractionr<image_segmentationr=image_to_imager> image_to_textr?mask_generationr@object_detectionrAquestion_answeringrBrCtable_question_answeringrDrEtext2text_generationrFrGrHtext_classificationrItext_generationrJ text_to_audiorKtoken_classificationrLrMrNrOvideo_classificationrPvisual_question_answeringrQzero_shot_audio_classificationrRzero_shot_classificationrSrTzero_shot_image_classificationrUzero_shot_object_detectionrV tensorflowrmodels.auto.modeling_tf_autorWrXrYrZr[r\r]r^r_r`rarrbrcrdrerfrgrhrirjrkrlrmrnrorprqrrrsrtrurvrwrxrymodeling_tf_utilsrzmodeling_utilsr{tokenization_utils_fastr| get_loggerrr TASK_ALIASESSUPPORTED_TASKSsetrrrrrrrvaluesaddrrrrrrrboolintrLrrrrs IIIIIIIIIIIIIIIIII&&&&&&222222@@@@@@AAAAAA777777777777aaaaaaaa[[[[[[[[]]]]]]]]JJJJJJJJLLLLLLLL------444444                            >=====LLLLLL                        655555JJJJJJ999999''''''======DDDDDD999999000000......333333555555[[[[[[[[kkkkkkkkiiiiiiiiii;;;;;;333333...... >=====FFFFFFOOOOOOkkkkkkkkOOOOOOGGGGGG?                          LLL8B555555000000AAAAAA  H % % 0 ! &%  O+4F4F4H4HP.00bd$QRS O#2>P>P>R>RZ 9::XZd$NOP %%O#M_M_MaMai)+HIIgid$BCD O,) / 1 19{nnr0022:yll EE   -OD*9H9J9JR355PR7I7I7K7KS133QS __   EO\+6Eo6G6GO022R4F4F4H4HP.00b UU   ]Ot)4CO4E4EM.0022D2D2F2FN,..B UU   uOL.7I7I7K7KS133QS9H9J9JR355PR DD  ! !MOd /8J8J8L8LT244RT dJK ""eOv"1:L:L:N:NV466TV dFG $$wOH +:?+<+<D%''"););)=)=E#%%2 BB   IO`%,;O,=,=E&((2*<*<*>*>F$&&B HPqrr aOt#,;O,=,=E&((2*<*<*>*>F$&&B"+KSs$t$tu"+KSs$t$tu"+KSs$t$tu    uOJ+,;O,=,=E&((2*<*<*>*>F$&&B$DLlmmn KOX&+:?+<+<D%''"););)=)=E#%%2$HPtuuv YOf.9H9J9JR355PR7I7I7K7KS133QS>B >B   !!gOF%3>Mo>O>OW8::UW->F'))B+=+=+?+?G%''R ==   (0B0B0D0DL*,,"d$JKL 08J8J8L8LT244RTd$MNO ##(0B0B0D0DL*,,"d$BCD ,4F4F4H4HP.00bd$[\] '/A/A/C/CK)++d$HIJ %-?-?-A-AI'))rd$TUV QOOOb!SUU355SUU :::2-.-.-.-.`   "JN59VZJN@D6:#"(,8<(,#'$(#b Qb Q b Q E#02EEF Gb Q U3 001 2b Qc#68QQRS b Q  c+E&E FG b Q eC);$;<= b Qc>123b Q}b Qsmb Qb Q E#t)$ %b Q U3^34 5b Q ~b Q sCx.!b Q"SM#b Q&'b Qb Qb Qb Qb Qb Qr