ZjSrSSKJr SSKJr SSKJrJr SSKJ r J r \R"\ 5r \"SS 9\"S S \555r\"SS 9\"S S \555r\"SS 9\"SS\555r/SQrg)zIdefics2 model configuration)strict)PreTrainedConfig)auto_docstringlogging)CONFIG_MAPPING AutoConfigzHuggingFaceM4/idefics2-8b) checkpointc\rSrSr%SrSrSrSr\\ S'Sr \\ S'S r \\ S 'S r \\ S 'S r \\ S 'Sr\\\-\\\4-\ S'Sr\\\-\\\4-\ S'Sr\\ S'Sr\\ S'Sr\\-\ S'Sr\\ S'Srg)Idefics2VisionConfigaY Example: ```python >>> from transformers.models.idefics2.modeling_idefics2 import Idefics2VisionTransformer >>> from transformers.models.idefics2.configuration_idefics2 import Idefics2VisionConfig >>> # Initializing a Idefics2VisionConfig with google/siglip-base-patch16-224 style configuration >>> configuration = Idefics2VisionConfig() >>> # Initializing a Idefics2VisionTransformer (with random weights) from the google/siglip-base-patch16-224 style configuration >>> model = Idefics2VisionTransformer(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```idefics2_vision vision_configi hidden_sizei intermediate_size num_hidden_layersnum_attention_headsr num_channels image_size patch_sizegelu_pytorch_tanh hidden_actư>layer_norm_epsattention_dropout{Gz?initializer_rangeN)__name__ __module__ __qualname____firstlineno____doc__ model_typebase_config_keyrint__annotations__rrrrrlisttuplerrstrrfloatr r"__static_attributes__r#ڄ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/idefics2/configuration_idefics2.pyr r s "#J%OK!s!s!!L#47Jd3i%S/1746Jd3i%S/16)J) NE %(us{(#u#r2r c\rSrSr%SrSrSr\\S'Sr \ \S'Sr \ \S 'S r \ \S 'S r\ \S 'Sr\ \S'Sr\ \S'Sr\ \S'Sr\ \ -\S'Sr\ \S'SrSrg)Idefics2PerceiverConfig=a4 resampler_n_latents (`int`, *optional*, defaults to 64): Number of latent embeddings to resample ("compress") the input sequence to (usually < 128). resampler_depth (`int`, *optional*, defaults to 3): Depth of the Perceiver Resampler (Transformer w/ cross attention). Should be shallow (<= 3). resampler_n_heads (`int`, *optional*, defaults to 16): Number of heads in each Transformer block (for multi-headed self-attention). resampler_head_dim (`int`, *optional*, defaults to 96): Dimensionality of each head projection in the Transformer block. idefics2_perceiversilurirr rms_norm_eps@resampler_n_latentsrresampler_depthresampler_n_heads`resampler_head_dimnum_key_value_headsrr r!r"cURUR:a%[SURSUR35eg)zOPart of `@strict`-powered validation. Validates the architecture of the config.znum_key_value_heads=z1 must be less than or equal to resampler_n_heads=N)rBr> ValueError)selfs r3validate_architecture-Idefics2PerceiverConfig.validate_architectureXsM  # #d&<&< <&t'?'?&@A&&*&<&<%=?  =r2r#N)r$r%r&r'r(r)rr/r,rr+r9r0r;r<r>r@rBr r"rFr1r#r2r3r5r5=s &JJKL%!!OSs    %(us{(#u#r2r5c^\rSrSr%SrSr\\\S.r Sr \ \ S'Sr \\ S'S r\ \ S 'S r\\-S -\ S 'S r\\-S -\ S 'S r\\-S -\ S'U4SjrSrU=r$)Idefics2Configaa perceiver_config (`IdeficsPerceiverConfig` or `dict`, *optional*): Custom perceiver config or dict Example: ```python >>> from transformers import Idefics2Model, Idefics2Config >>> # Initializing configuration >>> configuration = Idefics2Config() >>> # Initializing a model from the configuration >>> model = Idefics2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```idefics2) text_configperceiver_configrT use_cachei}image_token_idFtie_word_embeddingsNrrMrLc @>URc%[5Ul[RS5 O9[ UR[ 5(a[S 0URD6UlUR c%[5Ul[RS5 O9[ UR [ 5(a[S 0UR D6Ul[ UR[ 5(aUURRSS5URS'[URS"S 0URD6UlO6URc)[RS5 [S"SSSS 9UlURRURR:wa_URRURl URRURl [RS 5 [TU]<"S 0UD6 g) Nz7perciver_config is None, using default perceiver configz2vision_config is None, using default vision configr)mistralz.text_config is None, using default text configigh㈵>r)max_position_embeddingsr9 pad_token_idzPerceiver config has a different `hidden_size` than text config, which means default values were used. In your model's config on the hub, add `hidden_size` and `rms_norm_eps` keys under the `perceiver_config` dict. r#)rMr5loggerinfo isinstancedictrr rLgetr rr9 warning_oncesuper __post_init__)rEkwargs __class__s r3r\Idefics2Config.__post_init__s  ($;$=D ! KKQ R --t 4 4$;$Td>S>S$TD !    %!5!7D  KKL M **D 1 1!5!K8J8J!KD  d&& - --1-=-=-A-A,PY-ZD  \ *-d.>.>|.LMaPTP`P`aD     % KKH I-i8(0!  D     ' '4+@+@+L+L L040@0@0L0LD ! ! -151A1A1N1ND ! ! .   C  ''r2)rMrLr)r$r%r&r'r(r)r r5r sub_configsrNboolr,rOr+rPrrXrrMrLr\r1 __classcell__)r^s@r3rIrIas  J!3-K It NC %%48M4**T187;d--4;26K((4/6!(!(r2rI)rIr5r N)r(huggingface_hub.dataclassesrconfiguration_utilsrutilsrrautor r get_loggerr$rUr r5rI__all__r#r2r3ris#.3,-   H %67$+$8$D67.8D67?(%?(8?(D Pr2