+ jRt^RIHt^RIHt^RIHtHt]P!] 4t ]!RR7]!RR]444t ]!RR7]!RR ]444t ]!RR7]!R R ]444t .R OtR #)zMllama model configuration)strict)PreTrainedConfig)auto_docstringloggingzmeta-llama/Llama-3.2-11B-Vision) checkpointcaa]tRt^toRtRtRtRR/tRtRt ^ t ^t ^t ^t RtR tR t^tR t^tR tR tR tV3RltRt]V3RlRl4tV3RltRtVtV;t#)MllamaVisionConfigaV num_global_layers (`int`, *optional*, defaults to 8): Number of global layers in the Transformer encoder. Vision model has a second transformer encoder, called global. vision_output_dim (`int`, *optional*, defaults to 7680): Dimensionality of the vision model output. Includes output of transformer encoder with intermediate layers and global transformer encoder. max_num_tiles (`int`, *optional*, defaults to 4): Maximum number of tiles for image splitting. intermediate_layers_indices (`list[int]`, *optional*, defaults to [3, 7, 15, 23, 30]): Indices of intermediate layers of transformer encoder from which to extract and output features. These output features are concatenated with final hidden state of transformer encoder. supported_aspect_ratios (`list[list[int]]`, *optional*): List of supported aspect ratios for image splitting. If not specified, the default supported aspect ratios are [[1, 1], [1, 2], [1, 3], [1, 4], [2, 1], [2, 2], [3, 1], [4, 1]] for `max_num_tiles=4`. Example: ```python >>> from transformers import MllamaVisionConfig, MllamaVisionModel >>> # Initializing a Llama config >>> config = MllamaVisionConfig() >>> # Initializing a vision model from the mllama-11b style configuration >>> model = MllamaVisionModel(config) >>> # Accessing the model configuration >>> configuration = model.config ```mllama_vision_model vision_confignum_attention_headsattention_headsigeluiiih㈵>N{Gz?c <VPf ^^.^^.^^.^^.^^.^^.^^.^^..VnVPf .ROVn\SV` !R/VBR#)N))supported_aspect_ratiosintermediate_layers_indicessuper __post_init__selfkwargs __class__s&,p/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/mllama/configuration_mllama.pyr MllamaVisionConfig.__post_init__Msv  ' ' /-.FQFQFQFQPQFUVXYTZ]^`a\befhidj+kD (  + + 3/AD , ''c  VP^^.^^.^^.^^.^^.^^.^^.^^..8XdVP^8wd \R4hR#R#)zOPart of `@strict`-powered validation. Validates the architecture of the config.z;max_num_tiles must be 4 for default supported aspect ratiosN)r max_num_tiles ValueErrorrs&rvalidate_architecture(MllamaVisionConfig.validate_architectureUsr  ( (aVaVaVaVaQRVVWYZU[^_ab]cfgijek,l l""a'Z[ [( mr!c <V^8dQhRS[/#)return)int)format __classdict__s"r __annotate__MllamaVisionConfig.__annotate__^s11S1r!c,\VP4#)N)lenrr%s&rmax_aspect_ratio_id&MllamaVisionConfig.max_aspect_ratio_id]s4//00r!c<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[S[S[,,S[S[S[3,,;R &S[S[S[,,S[S[S[3,,;R &S[;R &S[;R &S[S[,R ,;R&S[S[S[,,R ,;R&S[;R&#)r) hidden_size hidden_actnum_hidden_layersnum_global_layersr num_channelsintermediate_sizevision_output_dim image_size patch_sizenorm_epsr#Nrrinitializer_range)r+strlisttuplefloat)r,r-s"rr.r/s&JKLMNOPQRSTUV!WX!YZd3i%S/17[\d3i%S/16]^_`ab"&cT!18cd"$s)_t3:ef#gr!)rr)__name__ __module__ __qualname____firstlineno____doc__ model_typebase_config_key attribute_mapr5r6r7r8r r9r:r;r<r=r>r#rrr?rr&propertyr2__annotate_func____static_attributes____classdictcell__ __classcell__rr-s@@rrrs <'J%O*,=>MKJOL!!47J46JHM486:#(\11Mr!rcaa]tRt^btoRtRtRtRtRtRt Rt ^(t ^ t ^t RtR tR tR tR tR tRtR tRtRtRtRtV3RltV3RltRtVtV;t#)MllamaTextConfiga cross_attention_layers (`list[int]`, *optional*): Indices of the cross attention layers. If not specified, will default to [3, 8, 13, 18, 23, 28, 33, 38]. Example: ```python >>> from transformers import MllamaTextModel, MllamaTextConfig >>> # Initializing a Mllama text config >>> config = MllamaTextConfig() >>> # Initializing a model from the Mllama text configuration >>> model = MllamaTextModel(config) >>> # Accessing the model configuration >>> configuration = model.config ```mllama_text_model text_configgAisilui8NrirTFgiiic V<VPf .ROVn\SV`!R/VBR#)N)r r!&r)cross_attention_layersrrrs&,rrMllamaTextConfig.__post_init__s'  & & .*HD ' ''r!cj<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[R,;R &S[;R &S[;R &S[;R &S[;R &S[;R&S[S[,R,;R&S[S[,;R&S[;R&S[S[S[,,R,;R&S[R,;R&#)r) vocab_sizer5r6r7r num_key_value_headsr:Nrope_parameters rms_norm_epsmax_position_embeddingsr? use_cachetie_word_embeddingsr_dropout bos_token_id eos_token_id pad_token_id)r+r@dictrCboolrA)r,r-s"rr.MllamaTextConfig.__annotate__bs)456789:;<!=> ?@#ABD['CDEF!*GH#IJKL%MN!I,3OPS[QRSTS /D(1UV*%Wr!)r_)rDrErFrGrHrIrJ default_thetarbr5r6r7r rcr:rdrerfr?rgrhr_rirjrkrlrrMrNrOrPrQs@@rrSrSbs &%J#OMJKJ! ##'OL#*#I %/3GL+1L%L([r!rScfaa]tRt^toRtRtRR/tR]R]/t Rt Rt Rt V3R lt V3R ltR tVtV;t#) MllamaConfiga\ Example: ```python >>> from transformers import MllamaForConditionalGeneration, MllamaConfig, MllamaVisionConfig, MllamaTextConfig >>> # Initializing a CLIP-vision config >>> vision_config = MllamaVisionConfig() >>> # Initializing a Llama config >>> text_config = MllamaTextConfig() >>> # Initializing a mllama-11b style configuration >>> configuration = MllamaConfig(vision_config, text_config) >>> # Initializing a model from the mllama-11b style configuration >>> model = MllamaForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```mllamaimage_token_idimage_token_indexrUr NrVc <VPf&\4Vn\PR4M:\ VP\ 4'd\R/VPBVnVP f&\4Vn\PR4M:\ VP \ 4'd\R/VP BVn\SV`$!R/VBR#)Nz9vision_config is None, using default mllama vision configz5text_config is None, using default mllama text configr) r rloggerinfo isinstancermrUrSrrrs&,rrMllamaConfig.__post_init__s    %!3!5D  KKS T **D 1 1!3!Id6H6H!ID     #/1D  KKO P (($ / //C$2B2BCD  ''r!cz<V^8dQh/S[S[,R,;R&S[S[,R,;R&S[;R&#)r)Nr rUru)rmrr+)r,r-s"rr.MllamaConfig.__annotate__sF>**T18?@((4/6AB#Cr!)rUr )rDrErFrGrHrIrKrSr sub_configsr rUrurrMrNrOrPrQs@@rrrrrsM ,J-M!"2OEWXK48M26K# (Gr!rrN)rrrSr)rHhuggingface_hub.dataclassesrconfiguration_utilsrutilsrr get_loggerrDrwrrSrr__all__rr!rrs!.3,   H %<=E1)E1>E1P<=.('.(>.(b<=.(#.(>.(b Er!