§ ‚ŠtjEãó„—dZddlmZddlmZddlmZed¬¦«eGd„d e¦«¦«¦«Zd gZd S) zFlaubert configurationé)Ústricté)ÚPreTrainedConfig)Úauto_docstringzflaubert/flaubert_base_uncased)Ú checkpointcót—eZdZUdZdZddddddd d œZd Zeed <d Z e e zed<dZ e ed<dZ e ed<dZe ed<dZe ed<dZe e zed<dZe e zed<dZeed<d Zeed<d Zeed<d Zeed<dZe ed<dZeed<dZe ed<d Ze ed!<d"Ze ed#<d$Ze ed%<d&Ze ed'<dZe ed(<d)Ze ed*<d+Ze ed,<d-Z e ed.<dZ!eed/<d0Z"e#ed1<dZ$eed2<d3Z%e#d3zed4<dZ&eed5<dZ'e e zed6<d-Z(e ed7<d-Z)e ed8<d&Z*e ed9<d&Z+e ed:<d)Z,e d3zed <d&Z-e d3zed<dZ.e e/e zd3zed<dZ0eed;<d3S)<ÚFlaubertConfigaÚ pre_norm (`bool`, *optional*, defaults to `False`): Whether to apply the layer normalization before or after the feed forward layer following the attention in each layer (Vaswani et al., Tensor2Tensor for Neural Machine Translation. 2018) emb_dim (`int`, *optional*, defaults to 2048): The dimensionality of embedding layer. gelu_activation (`bool`, *optional*, defaults to True): Whether to use GeLU activation function. sinusoidal_embeddings (`bool`, *optional*, defaults to `False`): Whether or not to use sinusoidal positional embeddings instead of absolute positional embeddings. causal (`bool`, *optional*, defaults to `False`): Whether or not the model should behave in a causal manner. Causal models use a triangular attention mask in order to only attend to the left-side context instead if a bidirectional context. asm (`bool`, *optional*, defaults to `False`): Whether or not to use an adaptive log softmax projection layer instead of a linear layer for the prediction layer. n_langs (`int`, *optional*, defaults to 1): The number of languages the model handles. Set to 1 for monolingual models. use_lang_emb (`bool`, *optional*, defaults to `True`) Whether to use language embeddings. Some models use additional language embeddings, see [the multilingual models page](http://huggingface.co/transformers/multilingual.html#xlm-language-embeddings) for information on how to use them. embed_init_std (`float`, *optional*, defaults to 2048^-0.5): The standard deviation of the truncated_normal_initializer for initializing the embedding matrices. embed_init_std (`float`, *optional*, defaults to `2048**-0.5`): Initializer std for embedding layers. bos_index (`int`, *optional*, defaults to 0): The index of the beginning of sentence token in the vocabulary. eos_index (`int`, *optional*, defaults to 1): The index of the end of sentence token in the vocabulary. pad_index (`int`, *optional*, defaults to 2): The index of the padding token in the vocabulary. unk_index (`int`, *optional*, defaults to 3): The index of the unknown token in the vocabulary. mask_index (`int`, *optional*, defaults to 5): The index of the masking token in the vocabulary. is_encoder (`bool`, *optional*, defaults to True): Whether the model is used as an encoder. summary_type (`string`, *optional*, defaults to "first"): Argument used when doing sequence summary. Used in the sequence classification and multiple choice models. 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 sequence classification and multiple choice models. Whether or not to add a projection after the vector extraction. summary_activation (`str`, *optional*): Argument used when doing sequence summary. Used in the sequence classification and multiple choice models. 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`): Used in the sequence classification and multiple choice models. Whether the projection outputs should have `config.num_labels` or `config.hidden_size` classes. summary_first_dropout (`float`, *optional*, defaults to 0.1): Used in the sequence classification and multiple choice models. The dropout ratio to be used after the projection and activation. start_n_top (`int`, *optional*, defaults to 5): Used in the SQuAD evaluation script. end_n_top (`int`, *optional*, defaults to 5): Used in the SQuAD evaluation script. mask_token_id (`int`, *optional*, defaults to 0): Model agnostic parameter to identify masked tokens when generating text in an MLM context. lang_id (`int`, *optional*, defaults to 1): The ID of the language used by the model. This parameter is used when generating text in a given language. ÚflaubertÚemb_dimÚn_headsÚn_layersÚ vocab_sizeÚ bos_token_idÚ eos_token_idÚ pad_token_id)Ú hidden_sizeÚnum_attention_headsÚnum_hidden_layersÚn_wordsÚ bos_indexÚ eos_indexÚ pad_indexFÚpre_normgÚ layerdropiÁuié égš™™™™™¹?ÚdropoutÚattention_dropoutTÚgelu_activationÚsinusoidal_embeddingsÚcausalÚasméÚn_langsÚ use_lang_embiÚmax_position_embeddingsgÍ;fž –?Úembed_init_stdgê-™—q=Úlayer_norm_epsg{®Gáz”?Úinit_stdrrrérrÚ unk_indexéÚ mask_indexÚ is_encoderÚfirstÚ summary_typeÚsummary_use_projNÚsummary_activationÚsummary_proj_to_labelsÚsummary_first_dropoutÚ start_n_topÚ end_n_topÚ mask_token_idÚlang_idÚtie_word_embeddings)1Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚ attribute_maprÚboolÚ__annotations__rÚfloatÚintrr r r rrrr r!r"r$r%r&r'r(r)rrrr+r-r.r0Ústrr1r2r3r4r5r6r7r8rrrÚlistr9©óúq/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/flaubert/configuration_flaubert.pyr r sÊ€€€€€€ðBðBðH€Jà Ø(Ø'ØØ#Ø#Ø#ðð€Mð€HˆdÐÐÑØ €Iˆus‰{Ð Ð Ñ Ø€JÐÐÑØ€GˆSÐÐÑØ€HˆcÐÐÑØ€GˆSÐÐÑØ€GˆUS‰[ÐÐÑØ%(Ðu˜s‘{Ð(Ð(Ñ(Ø €OTÐ Ð Ñ Ø"'И4Ð'Ð'Ñ'Ø€FˆDÐÐÑØ€CˆÐÐÑØ€GˆSÐÐÑØ€L$ÐÐÑØ#&ИSÐ&Ð&Ñ&Ø&€NEÐ&Ð&Ñ&Ø!€NEÐ!Ð!Ñ!Ø€HˆeÐÐÑØ€IˆsÐÐÑØ€IˆsÐÐÑØ€IˆsÐÐÑØ€IˆsÐÐÑØ€JÐÐÑØ€JÐÐÑØ€L#ÐÐÑØ!ÐdÐ!Ð!Ñ!Ø%)И˜d™ Ð)Ð)Ñ)Ø#'ИDÐ'Ð'Ñ'Ø),И5 3™;Ð,Ð,Ñ,Ø€KÐÐÑØ€IˆsÐÐÑØ€M3ÐÐÑØ€GˆSÐÐÑØ €L#˜‘*Ð Ð Ñ Ø €L#˜‘*Ð Ð Ñ Ø+,€L#˜˜Sœ ‘/ DÑ(Ð,Ð,Ñ,Ø $ИÐ$Ð$Ñ$Ð$Ð$rGr N) r=Úhuggingface_hub.dataclassesrÚconfiguration_utilsrÚutilsrr Ú__all__rFrGrHúrMsªððÐà.Ð.Ð.Ð.Ð.Ð.à3Ð3Ð3Ð3Ð3Ð3Ø#Ð#Ð#Ð#Ð#Ð#ð€Ð;Ð<Ñ<Ô<Øðt%ðt%ðt%ðt%ðt%Ð%ñt%ôt%ñ„ñ=Ô<ðt%ðn Ð €€€rG