+ j%/^RIHt^RIHt^RIHtHt]P!]4t ]!RR7]!RR]444t ]!RR7]!RR ]444t ]!RR7]!R R ]444t .R Ot R #))strict)PreTrainedConfig)auto_docstringloggingzCIDAS/clipseg-rd64) checkpointcva]tRt^toRtRtRtRtRtRt ^ t ^t ^Mt Rt RtR tR tR t^tR tR tRtV3RltRtVtR#)CLIPSegTextConfiga Example: ```python >>> from transformers import CLIPSegTextConfig, CLIPSegTextModel >>> # Initializing a CLIPSegTextConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegTextConfig() >>> # Initializing a CLIPSegTextModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```clipseg_text_model text_configi quick_geluh㈵>{Gz??iic VPVP,^8wd'\RVP RVP R24hR#zOPart of `@strict`-powered validation. Validates the architecture of the config.zThe hidden size (z6) is not a multiple of the number of attention heads (z).N hidden_sizenum_attention_heads ValueErrorselfs&r/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/clipseg/configuration_clipseg.pyvalidate_architecture'CLIPSegTextConfig.validate_architectureES   d66 6! ;#D$4$4#5622327  <cF<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[R,;R &S[S[,R,;R &S[;R &S[R,;R &S[R,;R &S[R,;R&S[S[S[,,R,;R&#) vocab_sizerintermediate_sizenum_hidden_layersrmax_position_embeddings hidden_actNlayer_norm_epsattention_dropoutinitializer_rangeinitializer_factor pad_token_id bos_token_id eos_token_id)intstrfloatlist)format __classdict__s"r __annotate__CLIPSegTextConfig.__annotate__s,-./0!1234 56!%78"9:DL';<U{T)/=>#?@ *AH* IJ*$KLS /D(0MrN)__name__ __module__ __qualname____firstlineno____doc__ model_typebase_config_keyr"rr#r$rr%r&r'r(r)r*r+r,r-r__annotate_func____static_attributes____classdictcell__r3s@rr r sr &J#OJK! #%"J#'N,/#'* !L$L+0LQrr cna]tRt^NtoRtRtRtRtRt^ t ^ t ^t ^t ^ t RtRtRtR tR tR tV3R ltR tVtR#)CLIPSegVisionConfiga Example: ```python >>> from transformers import CLIPSegVisionConfig, CLIPSegVisionModel >>> # Initializing a CLIPSegVisionConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegVisionConfig() >>> # Initializing a CLIPSegVisionModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```clipseg_vision_model vision_configii rrrrrc VPVP,^8wd'\RVP RVP R24hR#rrrs&rr)CLIPSegVisionConfig.validate_architectureqrrcp<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[S[S[,,S[S[S[3,,R,;R&S[S[S[,,S[S[S[3,,R,;R&S[;R &S[;R &S[S[,R,;R &S[;R &S[;R &#)r!rr#r$r num_channelsN image_size patch_sizer&r'r(r)r*)r.r1tupler/r0)r2r3s"rr4 CLIPSegVisionConfig.__annotate__Ns,-.!/012!3456d3i%S/1D8>78d3i%S/1D8=9:";< =>U{T)/?@#AB#Crr6N)r7r8r9r:r;r<r=rr#r$rrIrJrKr&r'r(r)r*rr>r?r@rAs@rrCrCNse (J%OK!!L;>J;=J"J N,/# #GrrCcaa]tRt^ztoRtRtR]R]/tRt Rt Rt Rt Rt Rt^@t^tR tR tR t^tR tV3R ltV3RltRtVtV;t#) CLIPSegConfiga extract_layers (`list[int]`, *optional*, defaults to `[3, 6, 9]`): Layers to extract when forwarding the query image through the frozen visual backbone of CLIP. reduce_dim (`int`, *optional*, defaults to 64): Dimensionality to reduce the CLIP vision embedding. conditional_layer (`int`, *optional*, defaults to 0): The layer to use of the Transformer encoder whose activations will be combined with the condition embeddings using FiLM (Feature-wise Linear Modulation). If 0, the last layer is used. use_complex_transposed_convolution (`bool`, *optional*, defaults to `False`): Whether to use a more complex transposed convolution in the decoder, enabling more fine-grained segmentation.. Example: ```python >>> from transformers import CLIPSegConfig, CLIPSegModel >>> # Initializing a CLIPSegConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegConfig() >>> # Initializing a CLIPSegModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a CLIPSegConfig from a CLIPSegTextConfig and a CLIPSegVisionConfig >>> # Initializing a CLIPSegText and CLIPSegVision configuration >>> config_text = CLIPSegTextConfig() >>> config_vision = CLIPSegVisionConfig() >>> config = CLIPSegConfig(text_config=config_text, vision_config=config_vision) ```clipsegr rENr g/L F@rrrr Fc 6<VPf/p\PR4MG\VP\4'dVPP 4pM VPpVP f/p\PR4MG\VP \4'dVP P 4pM VP pVPRR4pVPRR4pVe\ R/VBP 4pVP4FPwrxWr9gK WV,8wgKVR8wgK%Wt9d RV RV R2p MR V R 2p \PV 4KR VPV4Ve\R/VBP 4p R V 9d9V R ,P4UUu/uFwrx\V4VbK uppV R &V P4FPwrxWs9gK WV,8wgKVR8wgK%Wu9d RV R V R2p MR V R 2p \PV 4KR VPV 4\ R/VBVn\R/VBVn\S V`4!R/VBR#uuppi)NzR`text_config` is `None`. Initializing the `CLIPSegTextConfig` with default values.zV`vision_config` is `None`. initializing the `CLIPSegVisionConfig` with default values.text_config_dictvision_config_dicttransformers_version`zp` is found in both `text_config_dict` and `text_config` but with different values. The value `text_config_dict["z"]` will be used instead.zj`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["z"]` will be overridden.id2labelzv` is found in both `vision_config_dict` and `vision_config` but with different values. The value `vision_config_dict["zp`vision_config_dict` is provided which will be used to initialize `CLIPVisionConfig`. The value `vision_config["r6)r loggerinfo isinstancer to_dictrErCpopitemsupdater/super __post_init__) rkwargsr rErRrS_text_config_dictkeyvaluemessage_vision_config_dict __class__s &, rr_CLIPSegConfig.__post_init__s    #K KKl m ((*; < <**224K**K    %M KKp q **,? @ @ ..668M ..M "::&8$?#ZZ(r?r@ __classcell__)rfr3s@@rrOrOzsy! FJ "3_FYZK37K7;M!$N17'*2;NJ'(-0*%)/4&Q(qrrON)rOr rC)huggingface_hub.dataclassesrconfiguration_utilsrutilsrr get_loggerr7rWr rCrO__all__r6rrrs(/3,   H %/0,(,1,^/0'*'1'T/0G($G(1G(T Hr