+ j !Rt^RIHt^RIHt^RIHtHt]P!] 4t ]!RR7]!RR]444t ]!RR7]!RR ]444t ]!RR7]!R R ]444t .R OtR #)zALIGN model configuration)strict)PreTrainedConfig)auto_docstringloggingzkakaobrain/align-base) checkpointcta]tRt^toRtRtRtRtRt^ t ^ t Rt Rt Rt RtR t^tR tR t^tR tR tV3R ltRtVtR #)AlignTextConfiga Example: ```python >>> from transformers import AlignTextConfig, AlignTextModel >>> # Initializing a AlignTextConfig with kakaobrain/align-base style configuration >>> configuration = AlignTextConfig() >>> # Initializing a AlignTextModel (with random weights) from the kakaobrain/align-base style configuration >>> model = AlignTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```align_text_model text_configi:wii gelug?i{Gz?g-q=Nc8<V^8dQh/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 ,;R&S[R ,;R&S[S[S[,,R ,;R&#) vocab_size hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsN pad_token_id bos_token_id eos_token_id)intstrfloatlist)format __classdict__s"n/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/align/configuration_align.py __annotate__AlignTextConfig.__annotate__s,-./012!34!5678*9:#(#+3;<!&=>?@#AB!CD* EF*#GHS /D(/I)__name__ __module__ __qualname____firstlineno____doc__ model_typebase_config_keyrrrrrrrrrrrrrrr__annotate_func____static_attributes____classdictcell__)r#s@r$rrsp $J#OJK!!J'*03 #&O#!N L#L+/LIr'rcaa]tRt^@toRtRtRt^tRtRt Rt ^t Rt Rt RtRtRtRtRtRtRtR tR tR tR tR tRtV3RltV3RltRtVtV;t#)AlignVisionConfigaC width_coefficient (`float`, *optional*, defaults to 2.0): Scaling coefficient for network width at each stage. depth_coefficient (`float`, *optional*, defaults to 3.1): Scaling coefficient for network depth at each stage. depth_divisor (`int`, *optional*, defaults to 8): A unit of network width. kernel_sizes (`list[int]`, *optional*, defaults to `[3, 3, 5, 3, 5, 5, 3]`): List of kernel sizes to be used in each block. in_channels (`list[int]`, *optional*, defaults to `[32, 16, 24, 40, 80, 112, 192]`): List of input channel sizes to be used in each block for convolutional layers. out_channels (`list[int]`, *optional*, defaults to `[16, 24, 40, 80, 112, 192, 320]`): List of output channel sizes to be used in each block for convolutional layers. depthwise_padding (`list[int]`, *optional*, defaults to `[]`): List of block indices with square padding. strides (`list[int]`, *optional*, defaults to `[1, 2, 2, 2, 1, 2, 1]`): List of stride sizes to be used in each block for convolutional layers. num_block_repeats (`list[int]`, *optional*, defaults to `[1, 2, 2, 3, 3, 4, 1]`): List of the number of times each block is to repeated. expand_ratios (`list[int]`, *optional*, defaults to `[1, 6, 6, 6, 6, 6, 6]`): List of scaling coefficient of each block. squeeze_expansion_ratio (`float`, *optional*, defaults to 0.25): Squeeze expansion ratio. hidden_dim (`int`, *optional*, defaults to 1280): The hidden dimension of the layer before the classification head. pooling_type (`str` or `function`, *optional*, defaults to `"mean"`): Type of final pooling to be applied before the dense classification head. Available options are [`"mean"`, `"max"`] batch_norm_momentum (`float`, *optional*, defaults to 0.99): The momentum used by the batch normalization layers. drop_connect_rate (`float`, *optional*, defaults to 0.2): The drop rate for skip connections. Example: ```python >>> from transformers import AlignVisionConfig, AlignVisionModel >>> # Initializing a AlignVisionConfig with kakaobrain/align-base style configuration >>> configuration = AlignVisionConfig() >>> # Initializing a AlignVisionModel (with random weights) from the kakaobrain/align-base style configuration >>> model = AlignVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```align_vision_model vision_configiXg@g@g?swishi meanr gMbP?gGz?g?c <\VP4^,VnRF!p\W\ \ W444K# \ SV`!R/VBR#)N) kernel_sizes in_channels out_channelsdepthwise_paddingstridesnum_block_repeats expand_ratiosr()sumr@rsetattrr!getattrsuper __post_init__)selfkwargsattr __class__s&, r$rFAlignVisionConfig.__post_init__sO!$T%;%;!r?r@rAsqueeze_expansion_ratior hidden_dim pooling_typerbatch_norm_epsbatch_norm_momentumdrop_connect_rate)rr!tupler r)r"r#s"r$r%AlignVisionConfig.__annotate__@slmnd3i%S/17op"qr"stuvs)eCHo-EwxcU38_,Myzs)eCHo-O{|eCHo-2}~#YsCx (@@Cy5c?2JAB9uS#X.FCD#)EFGHIJKL#MN!OP%QRs{(Sr')r)rZrZr[r[rZ) (Pp)r]r^r_r`rarbi@r()rrrrcrrc)rcrrrZrZr:rc)rcrdrdrdrdrd) r)r*r+r,r-r.r/rMrNrOrPrQr;r<r=r>r?r@rArRrrSrTrrUrVrWrFr0r1r2 __classcell__rJr#s@@r$r4r4@s. `&J%OL47J""M0EL/MK0OL02+@G5J1FM%)JJL#!N!%%( (Wr'r4cfaa]tRt^toRtRtR]R]/tRt Rt Rt Rt Rt V3R ltV3R ltR tVtV;t#) AlignConfiga temperature_init_value (`float`, *optional*, defaults to 1.0): The initial value of the *temperature* parameter. Default is used as per the original ALIGN implementation. Example: ```python >>> from transformers import AlignConfig, AlignModel >>> # Initializing a AlignConfig with kakaobrain/align-base style configuration >>> configuration = AlignConfig() >>> # Initializing a AlignModel (with random weights) from the kakaobrain/align-base style configuration >>> model = AlignModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a AlignConfig from a AlignTextConfig and a AlignVisionConfig >>> from transformers import AlignTextConfig, AlignVisionConfig >>> # Initializing ALIGN Text and Vision configurations >>> config_text = AlignTextConfig() >>> config_vision = AlignVisionConfig() >>> config = AlignConfig(text_config=config_text, vision_config=config_vision) ```alignr r6Nig?r c <VPf&\4Vn\PR4M:\ VP\ 4'd\R/VPBVnVP f&\4Vn\PR4M:\ VP \ 4'd\R/VP BVn\SV`$!R/VBR#)NzP`text_config` is `None`. Initializing the `AlignTextConfig` with default values.zT`vision_config` is `None`. initializing the `AlignVisionConfig` with default values.r() r rloggerinfo isinstancedictr6r4rErF)rGrHrJs&,r$rFAlignConfig.__post_init__s    #.0D  KKj k (($ / /.B1A1ABD     %!2!4D  KKn o **D 1 1!2!HT5G5G!HD  ''r'c<V^8dQh/S[S[,R,;R&S[S[,R,;R&S[;R&S[;R&S[;R&#)rNr r6projection_dimtemperature_init_valuer)rnrrr )r"r#s"r$r%AlignConfig.__annotate__sfD((4/6EF**T18GHIJ"'KL#Mr')r r6)r)r*r+r,r-r.rr4 sub_configsr r6rqrrrrFr0r1r2rerfs@@r$rhrhsH 8J /?DUVK26K48MN$'# (Qr'rhN)rr4rh)r-huggingface_hub.dataclassesrconfiguration_utilsrutilsrr get_loggerr)rkrr4rh__all__r(r'r$rzs .3,   H %23"0&"04"0J23V((V(4V(r233("3(43(l Br'