U 9%e*@sdZddlmZddlmZmZmZmZmZddl m Z erLddl m Z m Z ddlmZddlmZmZdd lmZmZeeZd d d d dddZGdddeZGdddeZdS)z Bloom configuration) OrderedDict) TYPE_CHECKINGAnyListMappingOptional)version)PreTrainedTokenizer TensorType)PretrainedConfig)OnnxConfigWithPast PatchingSpec)is_torch_availableloggingz@https://huggingface.co/bigscience/bloom/resolve/main/config.jsonzBhttps://huggingface.co/bigscience/bloom-560m/blob/main/config.jsonzAhttps://huggingface.co/bigscience/bloom-1b1/blob/main/config.jsonzAhttps://huggingface.co/bigscience/bloom-1b7/blob/main/config.jsonz@https://huggingface.co/bigscience/bloom-3b/blob/main/config.jsonzAhttps://huggingface.co/bigscience/bloom-7b1/blob/main/config.json)zbigscience/bloomzbigscience/bloom-560mzbigscience/bloom-1b1zbigscience/bloom-1b7zbigscience/bloom-3bzbigscience/bloom-7b1cs6eZdZdZdZdgZdddZdfdd ZZS) BloomConfigaR This is the configuration class to store the configuration of a [`BloomModel`]. It is used to instantiate a Bloom model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to the Bloom architecture [bigscience/bloom](https://huggingface.co/bigscience/bloom). Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 250880): Vocabulary size of the Bloom model. Defines the maximum number of different tokens that can be represented by the `inputs_ids` passed when calling [`BloomModel`]. Check [this discussion](https://huggingface.co/bigscience/bloom/discussions/120#633d28389addb8530b406c2a) on how the `vocab_size` has been defined. hidden_size (`int`, *optional*, defaults to 64): Dimensionality of the embeddings and hidden states. n_layer (`int`, *optional*, defaults to 2): Number of hidden layers in the Transformer encoder. n_head (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer encoder. layer_norm_epsilon (`float`, *optional*, defaults to 1e-5): The epsilon to use in the layer normalization layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. apply_residual_connection_post_layernorm (`bool`, *optional*, defaults to `False`): If enabled, use the layer norm of the hidden states as the residual in the transformer blocks hidden_dropout (`float`, *optional*, defaults to 0.1): Dropout rate of the dropout function on the bias dropout. attention_dropout (`float`, *optional*, defaults to 0.1): Dropout rate applied to the attention probs use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). pretraining_tp (`int`, *optional*, defaults to `1`): Experimental feature. Tensor parallelism rank used during pretraining with Megatron. Please refer to [this document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is necessary to ensure exact reproducibility of the pretraining results. Please refer to [this issue](https://github.com/pytorch/pytorch/issues/76232). Note also that this is enabled only when `slow_but_exact=True`. slow_but_exact (`bool`, *optional*, defaults to `False`): Experimental feature. Whether to use slow but exact implementation of the attention mechanism. While merging the TP rank tensors, due to slicing operations the results may be slightly different between the model trained on Megatron and our model. Please refer to [this issue](https://github.com/pytorch/pytorch/issues/76232). A solution to obtain more accurate results is to enable this feature. Enabling this will hurt the computational time of the inference. Will be probably resolved in the future once the main model has been fine-tuned with TP_rank=1. Example: ```python >>> from transformers import BloomConfig, BloomModel >>> # Initializing a Bloom configuration >>> configuration = BloomConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = BloomModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zbloompast_key_valuesn_layern_head)Znum_hidden_layersnum_attention_heads@h㈵>{Gz?TFc s||_|dd}|dkr|n||_||_||_||_||_||_| |_| |_ | |_ | |_ ||_ | |_ ||_tjf|| d|dS)Nn_embed) bos_token_id eos_token_id) vocab_sizepop hidden_sizerrlayer_norm_epsiloninitializer_range use_cachepretraining_tp(apply_residual_connection_post_layernormhidden_dropoutattention_dropoutrr slow_but_exactsuper__init__)selfr!r#rrr$r%r&rr r(r)r*r'r+kwargsr __class__l/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/bloom/configuration_bloom.pyr-qs  zBloomConfig.__init__)rrrrrrTrrFrrrF) __name__ __module__ __qualname____doc__Z model_typeZkeys_to_ignore_at_inferenceZ attribute_mapr- __classcell__r2r2r0r3r*s*?rc seZdZedZdeeee e dfdd Z e e ee eeffdd d Ze edd d Ze edd dZe edddZddeee ede eefdfdd Ze edddZZS)BloomOnnxConfigz1.12defaultNF)configtaskpatching_specsuse_pastcs.tj||||dt|jdds*d|j_dS)N)r<r=r> pad_token_idr)r,r-getattr_configr?)r.r;r<r=r>r0r2r3r-szBloomOnnxConfig.__init__)returncCsJtddddi}|jr8|j|dddddd|d <nddd|d <|S) N input_idsbatchsequence)rrinputsT) directionZinverted_values_shapezpast_sequence + sequenceattention_mask)rr>Zfill_with_past_key_values_)r. common_inputsr2r2r3rFs zBloomOnnxConfig.inputscCs|jjSN)rArr.r2r2r3 num_layersszBloomOnnxConfig.num_layerscCs|jjSrJ)rArrKr2r2r3rsz#BloomOnnxConfig.num_attention_headscCsdS)NgMbP?r2rKr2r2r3atol_for_validationsz#BloomOnnxConfig.atol_for_validationr r ) tokenizer batch_size seq_lengthis_pair frameworkrBc stt|j|||||d}td|di}|jrts@tdnlddl|dj\}} | d} |j j |j } ||j | | f||j | | ffddt |j D|d<|d |d <|jr|d j} j|d j|| | d gd d |d <|S) N)rPrQrRrSrCzACannot generate dummy past_keys inputs without PyTorch installed.rrcs g|]}fqSr2)Zzeros).0_Zpast_key_shapeZpast_value_shapetorchr2r3 sz9BloomOnnxConfig.generate_dummy_inputs..rrH)dtyper)dim)r,r generate_dummy_inputsrr>r ValueErrorrWshaperAr#rrangerLrYcatZones) r.rOrPrQrRrSrIZordered_inputsrDZseqlenZpast_key_values_lengthZhead_dimZ mask_dtyper0rVr3r[sD      z%BloomOnnxConfig.generate_dummy_inputscCsdS)N r2rKr2r2r3default_onnx_opsetsz"BloomOnnxConfig.default_onnx_opset)r:NF)rNrNFN)r4r5r6rparseZtorch_onnx_minimum_versionr strrrboolr-propertyrintrFrLrfloatrMrrr[rar8r2r2r0r3r9s@    1r9N)r7 collectionsrtypingrrrrr packagingrr r Zconfiguration_utilsr Zonnxr rutilsrrZ get_loggerr4loggerZ#BLOOM_PRETRAINED_CONFIG_ARCHIVE_MAPrr9r2r2r2r3s$     n