§ ñ§gí!ãóÆ—dZddlmZddlmZmZmZmZmZddl m Z ddl m Z ddl mZer ddlmZmZmZeje¦«ZGd „d e ¦«ZGd „d e ¦«Zd S)zDeBERTa model configurationé)Ú OrderedDict)Ú TYPE_CHECKINGÚAnyÚMappingÚOptionalÚUnioné)ÚPretrainedConfig)Ú OnnxConfig)Úlogging)ÚFeatureExtractionMixinÚPreTrainedTokenizerBaseÚ TensorTypecóN‡—eZdZdZdZ dˆfd„ ZˆxZS)Ú DebertaConfigay This is the configuration class to store the configuration of a [`DebertaModel`] or a [`TFDebertaModel`]. It is used to instantiate a DeBERTa model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the DeBERTa [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Arguments: vocab_size (`int`, *optional*, defaults to 50265): Vocabulary size of the DeBERTa model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`DebertaModel`] or [`TFDebertaModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"`, `"gelu"`, `"tanh"`, `"gelu_fast"`, `"mish"`, `"linear"`, `"sigmoid"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (`int`, *optional*, defaults to 512): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). type_vocab_size (`int`, *optional*, defaults to 0): The vocabulary size of the `token_type_ids` passed when calling [`DebertaModel`] or [`TFDebertaModel`]. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. relative_attention (`bool`, *optional*, defaults to `False`): Whether use relative position encoding. max_relative_positions (`int`, *optional*, defaults to 1): The range of relative positions `[-max_position_embeddings, max_position_embeddings]`. Use the same value as `max_position_embeddings`. pad_token_id (`int`, *optional*, defaults to 0): The value used to pad input_ids. position_biased_input (`bool`, *optional*, defaults to `True`): Whether add absolute position embedding to content embedding. pos_att_type (`List[str]`, *optional*): The type of relative position attention, it can be a combination of `["p2c", "c2p"]`, e.g. `["p2c"]`, `["p2c", "c2p"]`. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. Example: ```python >>> from transformers import DebertaConfig, DebertaModel >>> # Initializing a DeBERTa microsoft/deberta-base style configuration >>> configuration = DebertaConfig() >>> # Initializing a model (with random weights) from the microsoft/deberta-base style configuration >>> model = DebertaModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ÚdebertaéYÄéé é Úgeluçš™™™™™¹?érç{®Gáz”?çH¯¼šò×z>FéÿÿÿÿTNc ó•—t¦«jdi|¤Ž||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ ||_ ||_||_t!|t"¦«r1d„| ¦« d¦«D¦«}||_||_| |_| d|¦«|_||_||_dS)Ncó6—g|]}| ¦«‘ŒS©)Ústrip)Ú.0Úxs úm/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/deberta/configuration_deberta.pyú z*DebertaConfig.__init__..‘s €ÐOÐOÐO¨!˜AŸGšG™IœIÐOÐOÐOóú|Úpooler_hidden_sizer)ÚsuperÚ__init__Ú hidden_sizeÚnum_hidden_layersÚnum_attention_headsÚintermediate_sizeÚ hidden_actÚhidden_dropout_probÚattention_probs_dropout_probÚmax_position_embeddingsÚtype_vocab_sizeÚinitializer_rangeÚrelative_attentionÚmax_relative_positionsÚ pad_token_idÚposition_biased_inputÚ isinstanceÚstrÚlowerÚsplitÚ pos_att_typeÚ vocab_sizeÚlayer_norm_epsÚgetr'Úpooler_dropoutÚpooler_hidden_act)Úselfr=r*r+r,r-r.r/r0r1r2r3r>r4r5r6r7r<r@rAÚkwargsÚ __class__s €r#r)zDebertaConfig.__init__gsø€ð. ‰ŒÔÐ"Ð"˜6Ð"Ð"Ð"à&ˆÔØ!2ˆÔØ#6ˆÔ Ø!2ˆÔØ$ˆŒØ#6ˆÔ Ø,HˆÔ)Ø'>ˆÔ$Ø.ˆÔØ!2ˆÔØ"4ˆÔØ&<ˆÔ#Ø(ˆÔØ%:ˆÔ"õ l¥CÑ (Ô (ð PØOÐO¨|×/AÒ/AÑ/CÔ/C×/IÒ/IÈ#Ñ/NÔ/NÐOÑOÔOˆLà(ˆÔØ$ˆŒØ,ˆÔà"(§*¢*Ð-AÀ;Ñ"OÔ"OˆÔØ,ˆÔØ!2ˆÔÐÐr%)rrrrrrrrrrrrFrrTNrr)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typer)Ú __classcell__©rDs@r#rr sŒø€€€€€ðB ðB ðH€JðØØØØØØØ%(Ø #ØØØØ Ø!ØØ"ØØØ ð)23ð23ð23ð23ð23ð23ð23ð23ð23ð23r%rcóà‡—eZdZedeeeeefffd„¦«Zedefd„¦«Z dd e d d ed ed ede de ddedededddeee ffˆfd„ Z ˆxZS)ÚDebertaOnnxConfigÚreturncóª—|jdkrddddœ}ndddœ}|jjdkrtd|fd |fd |fg¦«Std|fd |fg¦«S) Nzmultiple-choiceÚbatchÚchoiceÚsequence)réé)rrSrÚ input_idsÚattention_maskÚtoken_type_ids)ÚtaskÚ_configr2r)rBÚ dynamic_axiss r#ÚinputszDebertaOnnxConfig.inputsžs€à Œ9Ð)Ò )Ð )Ø&¨8¸ ÐCÐCˆLˆLà&¨:Ð6Ð6ˆLØ Œ<Ô '¨!Ò +Ð +Ýؘ|Ð,Ð/?ÀÐ.NÐQaÐcoÐPpÐqñôð õ ¨lÐ ;Ð>NÐP\Ð=]Ð^Ñ_Ô_Ð _r%có—dS)Nrr)rBs r#Údefault_onnx_opsetz$DebertaOnnxConfig.default_onnx_opset«s€àˆrr%rFNr é(Ú preprocessor)rr Ú batch_sizeÚ seq_lengthÚ num_choicesÚis_pairÚ frameworkrÚ num_channelsÚ image_widthÚ image_heightÚ tokenizerrc ó|•—t¦« ||¬¦«} |jjdkrd| vr| d=| S)N)r_rdrrW)r(Úgenerate_dummy_inputsrYr2) rBr_r`rarbrcrdrerfrgrhÚ dummy_inputsrDs €r#rjz'DebertaOnnxConfig.generate_dummy_inputs¯sLø€õ‘w”w×4Ò4À,ÐZcÐ4ÑdÔdˆ Ø Œ<Ô '¨1Ò ,Ð ,Ð1AÀ\Ð1QÐ1QØÐ-Ð.ØÐr%) rrrFNr r^r^N)rErFrGÚpropertyrr9Úintr[r]rÚboolrrrjrJrKs@r#rMrMsCø€€€€€Ø ð `˜  W¨S°#¨XÔ%6Ð 6Ô7ð `ð `ð `ñ„Xð `ðð Cðððñ„Xðð ØØØØ,0ØØØØ/3ððàÐOÔPððððð ð ð ð ð ð˜LÔ)ðððððððð-ðð cÔ ððððððððððr%rMN)rHÚ collectionsrÚtypingrrrrrÚconfiguration_utilsr Úonnxr Úutilsr Úr rrÚ get_loggerrEÚloggerrrMrr%r#úrws$ðð"Ð!à#Ð#Ð#Ð#Ð#Ð#Ø?Ð?Ð?Ð?Ð?Ð?Ð?Ð?Ð?Ð?Ð?Ð?Ð?Ð?à3Ð3Ð3Ð3Ð3Ð3ØÐÐÐÐÐØÐÐÐÐÐððPØOÐOÐOÐOÐOÐOÐOÐOÐOÐOð ˆÔ ˜HÑ %Ô %€ðy3ðy3ðy3ðy3ðy3Ð$ñy3ôy3ðy3ðz"ð"ð"ð"ð"˜ ñ"ô"ð"ð"ð"r%