o ¾e¦i%>ã@sTddlmZddlmZGdd„deƒZGdd„deƒZGdd„deƒZgd ¢Zd S) é)ÚPreTrainedConfig)ÚRopeParameterscsHeZdZdZdZdZ          d‡fdd„ Z‡ZS)ÚGlm4vVisionConfiga“ This is the configuration class to store the configuration of a [`Glm4vVisionModel`]. It is used to instantiate an Glm4vVisionModel model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of GLM-4.1V-9B-Thinking [THUDM/GLM-4.1V-9B-Thinking](https://huggingface.co/THUDM/GLM-4.1V-9B-Thinking). Args: depth (`int`, *optional*, defaults to 24): Number of layers (depth) in the model. hidden_size (`int`, *optional*, defaults to 1536): Dimensionality of the encoder layers and the pooler layer. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. attention_bias (`bool`, *optional*, defaults to `False`): Whether to add a bias to the queries, keys and values. attention_dropout (`float`, *optional*, defaults to 0.0): Dropout probability for attention weights. num_heads (``, *optional*, defaults to 12): in_channels (``, *optional*, defaults to 3): image_size (`int` or `list[int]`, *optional*, defaults to 336): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 14): The size (resolution) of each patch. rms_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the rms normalization layers. spatial_merge_size (`int`, *optional*, defaults to 2): The size used for merging spatial dimensions. temporal_patch_size (`int`, *optional*, defaults to 2): The size used for patches along the temporal dimension. out_hidden_size (`int`, *optional*, defaults to 4096): The output hidden size of the vision model. intermediate_size (`int`, *optional*, defaults to 13696): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Example: ```python >>> from transformers import Glm4vVisionConfig, Glm4vVisionModel >>> # Initializing a Glm4vVisionConfig GLM-4.1V-9B style configuration >>> configuration = Glm4vVisionConfig() >>> # Initializing a model (with random weights) from the GLM-4.1V-9B configuration >>> model = Glm4vVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Ú glm4v_visionÚ vision_configééÚsiluFçé réPéçñh㈵øä>ééé€5ç{®Gáz”?c sptƒjdi|¤Ž||_||_||_||_||_||_| |_| |_ | |_ | |_ ||_ ||_ | |_||_||_dS)N©)ÚsuperÚ__init__ÚdepthÚ hidden_sizeÚ hidden_actÚ num_headsÚ in_channelsÚ image_sizeÚ patch_sizeÚspatial_merge_sizeÚtemporal_patch_sizeÚout_hidden_sizeÚintermediate_sizeÚinitializer_rangeÚ rms_norm_epsÚattention_biasÚattention_dropout)Úselfrrrr#r$rrrrr"rrrr r!Úkwargs©Ú __class__rúk/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/glm4v/configuration_glm4v.pyrOs  zGlm4vVisionConfig.__init__)rrr Fr r rr r rrrrrr)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚbase_config_keyrÚ __classcell__rrr'r)rs(3ðrcseZdZdZdZdZdgZddddddd œZd gd gfd d gd gfd gd gfdœZ              d,de dBde dBde dBde dBd e dBd!e dBd"e dBd#e dBd$e dBd%e dBd&e dBd'e dBd(e ee e fBdBd)e dBf‡fd*d+„ Z‡ZS)-ÚGlm4vTextConfigaó This is the configuration class to store the configuration of a [`Glm4vModel`]. It is used to instantiate a GLM-4.1V model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of GLM-4.1V-9B-Thinking [THUDM/GLM-4.1V-9B-Thinking](https://huggingface.co/THUDM/GLM-4.1V-9B-Thinking). Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 151552): Vocabulary size of the Glm4v model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Glm4vModel`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 13696): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 40): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 32): Number of attention heads for each attention layer in the Transformer encoder. num_key_value_heads (`int`, *optional*, defaults to 2): This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details checkout [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `32`. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 32768): The maximum sequence length that this model might ever be used with. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rms_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the rms normalization layers. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. rope_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. pad_token_id (`int`, *optional*): The id of the padding token. ```python >>> from transformers import Glm4vTextModel, Glm4vConfig >>> # Initializing a GLM-4.1V style configuration >>> configuration = Glm4vConfig() >>> # Initializing a model from the GLM-4.1V style configuration >>> model = Glm4vTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Ú glm4v_textÚ text_configÚpast_key_valuesÚcolwiseÚrowwiseÚcolwise_gather_outputÚrowwise_split_input)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_up_projzlayers.*.mlp.down_projÚ input_idsÚ inputs_embedsÚ hidden_statesÚattention_mask)Ú embed_tokensÚlayersÚnorméPrré(é rr é€rrTr NÚ vocab_sizerr Únum_hidden_layersÚnum_attention_headsÚnum_key_value_headsrÚmax_position_embeddingsr!r"Ú use_cacher$Úrope_parametersÚ pad_token_idc s|||_||_||_||_||_||_|dur|}||_||_| |_| |_ | |_ | |_ | |_ ||_ tƒjdddhi|¤ŽdS)NÚignore_keys_at_rope_validationÚ mrope_sectionr)rDrHrr rErFrGrr!r"rIr$rJrKrr)r%rDrr rErFrGrrHr!r"rIr$rJrKr&r'rr)rÆs"zGlm4vTextConfig.__init__)r@rrrArBrr rCrrTr NN)r*r+r,r-r.r/Úkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planÚintÚstrÚfloatÚboolrÚdictrr0rrr'r)r1usv>ú  ýñþýüûúùø ÷ ö õ ô óòñr1csHeZdZdZdZeedœZdgZ      d‡fd d„ Z ‡Z S)Ú Glm4vConfigaô This is the configuration class to store the configuration of a [`Glm4vModel`]. It is used to instantiate a GLM-4.1V model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of GLM-4.1V-9B-Thinking [THUDM/GLM-4.1V-9B-Thinking](https://huggingface.co/THUDM/GLM-4.1V-9B-Thinking). Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: text_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `Glm4vTextConfig`): The config object or dictionary of the text backbone. vision_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `Glm4vVisionConfig`): The config object or dictionary of the vision backbone. image_token_id (`int`, *optional*, defaults to 151343): The image token index to encode the image prompt. video_token_id (`int`, *optional*, defaults to 151344): The video token index to encode the image prompt. image_start_token_id (`int`, *optional*, defaults to 151339): The image start token index to encode the start of image. image_end_token_id (`int`, *optional*, defaults to 151340): The image end token index to encode the end of image. video_start_token_id (`int`, *optional*, defaults to 151341): The video start token index to encode the start of video. video_end_token_id (`int`, *optional*, defaults to 151342): The video end token index to encode the end of video. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether the model's input and output word embeddings should be tied. ```python >>> from transformers import Glm4vForConditionalGeneration, Glm4vConfig >>> # Initializing a GLM-4.1V style configuration >>> configuration = Glm4vConfig() >>> # Initializing a model from the GLM-4.1V style configuration >>> model = Glm4vForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Úglm4v)rr3r4Né/Oé0Oé+Oé,Oé-Oé.OFc  s¸t|tƒr|jddi|¤Ž|_n |dur|jdƒ|_t|tƒr-|jddi|¤Ž|_n|dur<|jddi| ¤Ž|_||_||_||_||_||_ ||_ | |_ t ƒj di| ¤ŽdS)Nrr3r)Ú isinstancerUÚ sub_configsrr3Úimage_token_idÚvideo_token_idÚvideo_start_token_idÚvideo_end_token_idÚimage_start_token_idÚimage_end_token_idÚtie_word_embeddingsrr) r%r3rr`rardrerbrcrfr&r'rr)rs  zGlm4vConfig.__init__) NNrXrYrZr[r\r]F) r*r+r,r-r.rr1r_rNrr0rrr'r)rVïs+ örV)rVr1rN)Úconfiguration_utilsrÚmodeling_rope_utilsrrr1rVÚ__all__rrrr)Ús  ]z R