^j*ddlmZddlmZddlmZmZejeZ edeGddeZ edeGd d eZ edeGd d eZ gd Z y))strict)PreTrainedConfig)auto_docstringloggingz BAAI/AltCLIP) checkpointc2eZdZUdZdZdZdZeed<dZ eed<dZ eed <d Z eed <d Z eed <dZ eed<dZeed<dZedzed<dZeed<dZeed<dZedzed<dZedzed<dZedzed<dZeezed<dZeezed <dZeed!<d"Zeed#<d$Zy)%AltCLIPTextConfigaR project_dim (`int`, *optional*, defaults to 768): The dimensions of the teacher model before the mapping layer. Examples: ```python >>> from transformers import AltCLIPTextModel, AltCLIPTextConfig >>> # Initializing a AltCLIPTextConfig with BAAI/AltCLIP style configuration >>> configuration = AltCLIPTextConfig() >>> # Initializing a AltCLIPTextModel (with random weights) from the BAAI/AltCLIP style configuration >>> model = AltCLIPTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```altclip_text_model text_configi vocab_sizei hidden_sizeiintermediate_sizenum_hidden_layersnum_attention_headsimax_position_embeddingsgelu hidden_acth㈵>Nlayer_norm_eps{Gz?initializer_rangeinitializer_factor pad_token_idr bos_token_id eos_token_idg?hidden_dropout_probattention_probs_dropout_probtype_vocab_size project_dimc|j|jzdk7r&td|jd|jdyzOPart of `@strict`-powered validation. Validates the architecture of the config.rzThe hidden size (z6) is not a multiple of the number of attention heads (z).Nrr ValueErrorselfs |/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/altclip/configuration_altclip.pyvalidate_architecturez'AltCLIPTextConfig.validate_architectureGS   d66 6! ;#D$4$4#5622327  <)__name__ __module__ __qualname____doc__ model_typebase_config_keyr int__annotations__rrrrrrstrrfloatrrrrr r!r"r#r%r-r/r,r r s &&J#OJK!s!s!!#&S&J#'NEDL'#u# $$ L#*  L#*  L#* '*u*01 #+1OSKr/r c&eZdZUdZdZdZdZeed<dZ eed<dZ eed <d Z eed <d Z eed <d Z eed<dZeeezeeefzdzed<dZeeezeeefzdzed<dZeed<dZeed<dZeezdzed<dZeed<dZeed<dZy)AltCLIPVisionConfiga Example: ```python >>> from transformers import AltCLIPVisionConfig, AltCLIPVisionModel >>> # Initializing a AltCLIPVisionConfig with BAAI/AltCLIP style configuration >>> configuration = AltCLIPVisionConfig() >>> # Initializing a AltCLIPVisionModel (with random weights) from the BAAI/AltCLIP style configuration >>> model = AltCLIPVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```altclip_vision_model vision_configr$ri riprojection_dim rrr num_channelsN image_size patch_size quick_gelurrrgattention_dropoutrr?rc|j|jzdk7r&td|jd|jdyr'r(r*s r,r-z)AltCLIPVisionConfig.validate_architecturetr.r/)r0r1r2r3r4r5rr6r7rr?rrrArClisttuplerErr8rr9rGrrr-r:r/r,r<r<Ps (J%OK!s!NCs!!L#;>Jd3i%S/1D8>;=Jd3i%S/1D8="J" NE ,/sU{T)/#u# ##r/r<ceZdZUdZdZeedZdZe ezdze d<dZ e ezdze d<dZ e e d<d Zee zdze d <d Zedze d <fd ZxZS) AltCLIPConfiga Example: ```python >>> from transformers import AltCLIPConfig, AltCLIPModel >>> # Initializing a AltCLIPConfig with BAAI/AltCLIP style configuration >>> configuration = AltCLIPConfig() >>> # Initializing a AltCLIPModel (with random weights) from the BAAI/AltCLIP style configuration >>> model = AltCLIPModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a AltCLIPConfig from a AltCLIPTextConfig and a AltCLIPVisionConfig >>> # Initializing a AltCLIPText and AltCLIPVision configuration >>> config_text = AltCLIPTextConfig() >>> config_vision = AltCLIPVisionConfig() >>> config = AltCLIPConfig(text_config=config_text, vision_config=config_vision) ```altclip)r r>Nr r>r$r?g/L F@logit_scale_init_valuerHrc |ji}tjdnAt|jtr|jj }n |j}|j i}tjdnAt|j tr|j j }n |j }|jdd}|jdd}|t di|j }|jD]B\}}||vs |||k7s|dk7s||vr d|d|d} nd |d } tj| D|j||tdi|j } d | vr3| d jDcic]\}}t||c}}| d <| jD]B\}}||vs |||k7s|dk7s||vr d|d |d} nd |d } tj| D|j| t di||_tdi||_t |4di|ycc}}w)NzR`text_config` is `None`. Initializing the `AltCLIPTextConfig` with default values.zV`vision_config` is `None`. initializing the `AltCLIPVisionConfig` 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["r:)r loggerinfo isinstancer to_dictr>r<popitemsupdater8super __post_init__) r+kwargsr r>rQrR_text_config_dictkeyvaluemessage_vision_config_dict __class__s r,r^zAltCLIPConfig.__post_init__s    #K KKl m ((*; <**224K**K    %M KKp q **,? @ ..668M ..M "::&8$?#ZZ(r?r6rOr9rr^ __classcell__)res@r,rMrM}s} 0J"3FYZK37K))D077;M4--4;NC17ECK$.7'* *Q(Q(r/rM)r r<rMN)huggingface_hub.dataclassesrconfiguration_utilsrutilsrr get_loggerr0rVr r<rM__all__r:r/r,rns&/3,   H %>*/(/+/d>*(*(+(V>*t($t(+t(n Hr/