+ j Rt^RIHt^RIHt^RIHtHt]P!] 4t ]!RR7]!RR]444t ]!RR7]!RR ]444t ]!RR7]!R R ]444t .R OtR #)zPix2Struct model configuration)strict)PreTrainedConfig)auto_docstringloggingzgoogle/pix2struct-base) checkpointca]tRt^toRtRtR.tRRRRRRR RR RR RR R/tR tRt ^@t Rt ^ t ^ t ^ t^tRtRtRtRt^tRt^t^tRtRtRtRtV3RltRtVtR#)Pix2StructTextConfigan relative_attention_num_buckets (`int`, *optional*, defaults to 32): The number of buckets to use for each attention layer. relative_attention_max_distance (`int`, *optional*, defaults to 128): The maximum distance of the longer sequences for the bucket separation. dense_act_fn (`Union[Callable, str]`, *optional*, defaults to `"gelu_new"`): The non-linear activation function (function or string). Example: ```python >>> from transformers import Pix2StructTextConfig, Pix2StructTextModel >>> # Initializing a Pix2StructTextConfig with google/pix2struct-base style configuration >>> configuration = Pix2StructTextConfig() >>> # Initializing a Pix2StructTextModel (with random weights) from the google/pix2struct-base style configuration >>> model = Pix2StructTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```pix2struct_text_modelpast_key_values hidden_sizenum_attention_heads num_headsnum_hidden_layers num_layersdecoder_attention_headsencoder_attention_headsencoder_layersdecoder_layersiDg?ư>?gelu_newFNTcd<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[S[,;R &S[;R &S[;R &S[;R &S[;R &S[;R&S[R,;R&S[S[S[,,R,;R&S[R,;R&S[;R&S[;R&S[;R&#) vocab_sizer d_kvd_ffrr relative_attention_num_bucketsrelative_attention_max_distance dropout_ratelayer_norm_epsiloninitializer_factor dense_act_fndecoder_start_token_id use_cacheN pad_token_id eos_token_id bos_token_idtie_word_embeddings is_decoderadd_cross_attention)intfloatstrboollist)format __classdict__s"x/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/pix2struct/configuration_pix2struct.py __annotate__!Pix2StructTextConfig.__annotate__sILMNOP NQR STUVWX%(,YZ&).[\#+#]^$_`#ab"cd #efgh* ijS /D(,kl*#mn%opqr%s)__name__ __module__ __qualname____firstlineno____doc__ model_typekeys_to_ignore_at_inference attribute_maprr rrrr rrr r!r"r#r$r%r&r'r(r)r*r+__annotate_func____static_attributes____classdictcell__r2s@r3rrs .)J#4"5}{\!;!;,,MJKDDJI*,"+.# #L $ #"L"#I L+,L#L %J %sr6rcpa]tRt^UtoRtRtRtRtRt^@t ^ t ^ t Rt Rt RtRtRtR tR t^ t^tV3R ltR tVtR #)Pix2StructVisionConfiga* patch_embed_hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the input patch_embedding layer in the Transformer encoder. d_ff (`int`, *optional*, defaults to 2048): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. d_kv (`int`, *optional*, defaults to 64): Dimensionality of the key, query, value projections per attention head. The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"gelu"` are supported. dense_act_fn (`Union[Callable, str]`, *optional*, defaults to `"gelu_new"`): The non-linear activation function (function or string). seq_len (`int`, *optional*, defaults to 4096): Maximum sequence length (here number of patches) supported by the model. relative_attention_num_buckets (`int`, *optional*, defaults to 32): The number of buckets to use for each attention layer. relative_attention_max_distance (`int`, *optional*, defaults to 128): The maximum distance (in tokens) to use for each attention layer. Example: ```python >>> from transformers import Pix2StructVisionConfig, Pix2StructVisionModel >>> # Initializing a Pix2StructVisionConfig with google/pix2struct-base style configuration >>> configuration = Pix2StructVisionConfig() >>> # Initializing a Pix2StructVisionModel (with random weights) from the google/pix2struct-base style configuration >>> model = Pix2StructVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```pix2struct_vision_modelrrrrgg|=ric<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[S[,;R &S[S[,;R &S[;R &S[;R &S[;R &S[;R&S[;R&#)rr patch_embed_hidden_sizerrrr r#layer_norm_epsr attention_dropoutinitializer_ranger"seq_lenrr)r,r.r-)r1r2s"r3r4#Pix2StructVisionConfig.__annotate__UsLMN!&OP QR NSTUV!WX"YZ [\#+#]^s{(_`$ab#cdef%(,gh&).ir6r7N)r8r9r:r;r<r=r rHrrrr r#rIr rJrKr"rLrrr@rArBrCs@r3rErEUsm B+JK#&DD!"L N #L%($ #G*,"+.#ir6rEcnaa]tRt^toRtRtR]R]/tRt Rt Rt Rt Rt RtR tV3R ltV3R ltR tVtV;t#) Pix2StructConfiga is_vqa (`bool`, *optional*, defaults to `False`): Whether the model has been fine-tuned for VQA or not. Example: ```python >>> from transformers import Pix2StructConfig, Pix2StructForConditionalGeneration >>> # Initializing a Pix2StructConfig with google/pix2struct-base style configuration >>> configuration = Pix2StructConfig() >>> # Initializing a Pix2StructForConditionalGeneration (with random weights) from the google/pix2struct-base style configuration >>> model = Pix2StructForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a Pix2StructConfig from a Pix2StructTextConfig and a Pix2StructVisionConfig >>> # Initializing a Pix2Struct text and Pix2Struct vision configuration >>> config_text = Pix2StructTextConfig() >>> config_vision = Pix2StructVisionConfig() >>> config = Pix2StructConfig(text_config=config_text, vision_config=config_vision) ``` pix2struct text_config vision_configNrg{Gz?FTc |<VPf=\VPVPR7Vn\P R4Ml\ VP\4'dMVPVPR&VPVPR&\R/VPBVnVPf&\4Vn\P R4M:\ VP\4'd\R/VPBVnVPPVn VPPVn VPPVn VPVPn VPVPn \SV`<!R/VBR#)N)is_encoder_decoderr)zU`text_config` is `None`. initializing the `Pix2StructTextConfig` with default values.rTr)zY`vision_config` is `None`. initializing the `Pix2StructVisionConfig` with default values.r7)rQrrTr)loggerinfo isinstancedictrRrEr$r&r'rKsuper __post_init__)selfkwargs __class__s&,r3rZPix2StructConfig.__post_init__sU    #3#'#:#:$($<$< D  KKo p (($ / /595L5LD  1 26:6N6ND  2 33Gd6F6FGD     %!7!9D  KKs t **D 1 1!7!M$:L:L!MD &*&6&6&M&M# ,,99 ,,99-1-C-C*/3/E/E, ''r6c<V^8dQh/S[S[,R,;R&S[S[,R,;R&S[;R&S[;R&S[;R&S[;R&S[;R&#) rNrQrRr"rKis_vqar)rT)rXrr-r/)r1r2s"r3r4Pix2StructConfig.__annotate__sB((4/6CD**T18EF#GH#IJ KL%MN#Or6)r$r'r&rQrR)r8r9r:r;r<r=rrE sub_configsrQrRr"rKr`r)rTrZr@rArB __classcell__)r]r2s@@r3rOrOsU 6J "6I_`K26K48M ##F %#(Sr6rON)rOrrE)r<huggingface_hub.dataclassesrconfiguration_utilsrutilsrr get_loggerr8rUrrErO__all__r7r6r3ris%.3,   H %347&+7&57&t342/-2/52/j34@('@(5@(F Qr6