fTh/SrSSKJr SSKJrJrJrJr SSKJ r J r J r SSK J r SSKJrJr SSKJr \R&"\5r"S S \ 5r"S S \5rS S /rg )zOpenAI GPT-2 configuration) OrderedDict)AnyListMappingOptional)PreTrainedTokenizer TensorTypeis_torch_available)PretrainedConfig)OnnxConfigWithPast PatchingSpec)loggingcv^\rSrSrSrSrS/rSSSSS .rS U4S jjrS r U=r $) GPT2Configa This is the configuration class to store the configuration of a [`GPT2Model`] or a [`TFGPT2Model`]. It is used to instantiate a GPT-2 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 GPT-2 [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) architecture. 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 50257): Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`GPT2Model`] or [`TFGPT2Model`]. n_positions (`int`, *optional*, defaults to 1024): 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). n_embd (`int`, *optional*, defaults to 768): Dimensionality of the embeddings and hidden states. n_layer (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. n_head (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. n_inner (`int`, *optional*): Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd activation_function (`str`, *optional*, defaults to `"gelu_new"`): Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`. resid_pdrop (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. embd_pdrop (`float`, *optional*, defaults to 0.1): The dropout ratio for the embeddings. attn_pdrop (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention. layer_norm_epsilon (`float`, *optional*, defaults to 1e-05): 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. summary_type (`string`, *optional*, defaults to `"cls_index"`): Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`] and [`TFGPT2DoubleHeadsModel`]. Has to be one of the following options: - `"last"`: Take the last token hidden state (like XLNet). - `"first"`: Take the first token hidden state (like BERT). - `"mean"`: Take the mean of all tokens hidden states. - `"cls_index"`: Supply a Tensor of classification token position (like GPT/GPT-2). - `"attn"`: Not implemented now, use multi-head attention. summary_use_proj (`bool`, *optional*, defaults to `True`): Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`] and [`TFGPT2DoubleHeadsModel`]. Whether or not to add a projection after the vector extraction. summary_activation (`str`, *optional*): Argument used when doing sequence summary. Used in for the multiple choice head in [`GPT2DoubleHeadsModel`]. Pass `"tanh"` for a tanh activation to the output, any other value will result in no activation. summary_proj_to_labels (`bool`, *optional*, defaults to `True`): Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`] and [`TFGPT2DoubleHeadsModel`]. Whether the projection outputs should have `config.num_labels` or `config.hidden_size` classes. summary_first_dropout (`float`, *optional*, defaults to 0.1): Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`] and [`TFGPT2DoubleHeadsModel`]. The dropout ratio to be used after the projection and activation. scale_attn_weights (`bool`, *optional*, defaults to `True`): Scale attention weights by dividing by sqrt(hidden_size).. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). bos_token_id (`int`, *optional*, defaults to 50256): Id of the beginning of sentence token in the vocabulary. eos_token_id (`int`, *optional*, defaults to 50256): Id of the end of sentence token in the vocabulary. scale_attn_by_inverse_layer_idx (`bool`, *optional*, defaults to `False`): Whether to additionally scale attention weights by `1 / layer_idx + 1`. reorder_and_upcast_attn (`bool`, *optional*, defaults to `False`): Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention dot-product/softmax to float() when training with mixed precision. Example: ```python >>> from transformers import GPT2Config, GPT2Model >>> # Initializing a GPT2 configuration >>> configuration = GPT2Config() >>> # Initializing a model (with random weights) from the configuration >>> model = GPT2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```gpt2past_key_valuesn_embd n_positionsn_headn_layer) hidden_sizemax_position_embeddingsnum_attention_headsnum_hidden_layersc P>XlX lX0lX@lXPlX`lXplXlXlXl Xl Xl Xl Xl XlUUlUUlUUlUUlUUlUUlUUlUUl[.TU]`"SUUS.UD6 g)N) bos_token_id eos_token_id) vocab_sizerrrrn_inneractivation_function resid_pdrop embd_pdrop attn_pdroplayer_norm_epsiloninitializer_range summary_typesummary_use_projsummary_activationsummary_first_dropoutsummary_proj_to_labelsscale_attn_weights use_cachescale_attn_by_inverse_layer_idxreorder_and_upcast_attnrrsuper__init__)selfr!rrrrr"r#r$r%r&r'r(r)r*r+r-r,r.r/rrr0r1kwargs __class__s c/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/gpt2/configuration_gpt2.pyr3GPT2Config.__init__s6%&    #6 &$$"4!2( 0"4%:"&<#"4"/N,'>$(( XlXQWX)r#r&rr%rr(r'rrr"rrr1r$r0r.r+r,r-r)r*r/r!)iQii r:Ngelu_new皙?r<r<gh㈵>g{Gz? cls_indexTNTr<TTPr>FF) __name__ __module__ __qualname____firstlineno____doc__ model_typekeys_to_ignore_at_inference attribute_mapr3__static_attributes__ __classcell__r6s@r7rrs_ BJ#4"5#0'& M& #!(- %14Y4Yr9rc ^\rSrSrSS\S\S\\\S\ 4U4Sjjjr \ S\ \\ \ \444Sj5r\ S\ 4S j5r\ S\ 4S j5rSS \S \ S \ S\ S\\S\ \\44 U4Sjjjr\ S\ 4Sj5rSrU=r$)GPT2OnnxConfigconfigtaskpatching_specsuse_pastc~>[TU]XX4S9 [URSS5(dSURlgg)N)rNrOrP pad_token_idr)r2r3getattr_configrR)r4rMrNrOrPr6s r7r3GPT2OnnxConfig.__init__s; >]t||^T::()DLL %;r9returnc[SSSS.05nUR(aURUSS9 SSS.US'U$SSS.US'U$) N input_idsbatchsequence)rinputs) directionzpast_sequence + sequenceattention_mask)rrPfill_with_past_key_values_)r4 common_inputss r7r\GPT2OnnxConfig.inputssa#[g*2M$NO ==  + +MX + N29>X.YM* +3:j.IM* +r9c.URR$N)rTrr4s r7 num_layersGPT2OnnxConfig.num_layerss||###r9c.URR$rc)rTrrds r7r"GPT2OnnxConfig.num_attention_headss||"""r9 tokenizer batch_size seq_lengthis_pair frameworkc r>[[U] XX4US9n[SUS05nUR(a[ 5(d [ S5eSSKnUSRupU S-n U URU URRUR-4n [UR5V s/sH$oRU 5URU 54PM& sn US'USUS'UR(a6USRnWR!USUR#W W US9/S S 9US'U$s sn f) N)rjrkrlrmrXzACannot generate dummy past_keys inputs without PyTorch installed.rrr^)dtyper[)dim)r2r generate_dummy_inputsrrPr ValueErrortorchshaperrTrrangerezerosrpcatones)r4rirjrkrlrmr`ordered_inputsrtrYseqlenpast_key_values_length past_shape_ mask_dtyper6s r7rr$GPT2OnnxConfig.generate_dummy_inputss^0$M `iN %k=3M%NO ==%'' !dee -k : @ @ )/!&,,*LL,,0H0HH  QVVZVeVePf5Pf1[[,ekk*.EFPf501,99I+J'( =='(89??J/4yy 015::eE[cm:3nouv090N+ ,5s2+D4cg)N r rds r7default_onnx_opset!GPT2OnnxConfig.default_onnx_opset sr9r )defaultNF)rFN)r?r@rArBr strrrrboolr3propertyrintr\rerr r rrrrrGrHrIs@r7rKrKs(7; *  * *!l!34 *  * *WS#X%6 67$C$$#S## *. *&** *  * J' * c **XCr9rKN)rC collectionsrtypingrrrrr r r configuration_utilsr onnxr rutilsr get_loggerr?loggerrrK__all__r r9r7rsc !#//CC34   H %_Y!_YDN'Nb ) *r9