^j\ddlmZddlmZddlmZddlmZedeGdd eZedeGd d eZ edeGd d eZ gdZ y))strict)PreTrainedConfig)RopeParameters)auto_docstringzzai-org/GLM-4.1V-9B-Thinking) checkpointcFeZdZUdZdZdZdZeed<dZ eed<dZ e ed <d Z e ed <d Zeezed <dZeed<dZeed<dZeeezeeefzed<dZeeezeeefzed<dZeed<dZeed<dZeeezeeefzed<dZeed<dZeed<dZeed <y!)"Glm4vVisionConfiga, out_hidden_size (`int`, *optional*, defaults to 4096): The output hidden size of the vision model. 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 ``` glm4v_vision vision_configdepthi hidden_sizesilu hidden_actFattention_biasattention_dropout num_headsr in_channelsiP image_size patch_sizeh㈵> rms_norm_epsspatial_merge_sizetemporal_patch_sizeout_hidden_size5intermediate_size{Gz?initializer_rangeN)__name__ __module__ __qualname____doc__ model_typebase_config_keyrint__annotations__rrstrrboolrfloatrrrlisttuplerrrrr!r#r%x/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/glm4v/configuration_glm4v.pyr r s & J%OE3OKJ ND %(us{(IsK47Jd3i%S/1746Jd3i%S/16L%=>tCy5c?:>OS"s"#u#r4r cReZdZUdZdZdZdgZddddddd Zd gd gfd d gd gfd gd gfdZdhZ dZ e e d<dZ e e d<dZe e d<dZe e d<dZe e d<dZe dze d<dZee d<dZe e d <d!Zee d"<d#Zee d$<d%Zee d&<d'Zee ze d(<dZeezdze d)<dZe dze d*<fd+ZxZ S),Glm4vTextConfiga Example: ```python >>> from transformers import Glm4vTextModel, Glm4vConfig >>> # Initializing a GLM-4.1V style configuration >>> configuration = Glm4vConfig() >>> # Initializing a model from the GLM-4.1V style configuration >>> model = Glm4vTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` glm4v_text text_configpast_key_valuescolwiserowwisecolwise_gather_outputrowwise_split_input)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_up_projzlayers.*.mlp.down_proj input_ids inputs_embeds hidden_statesattention_mask) embed_tokenslayersnorm mrope_sectioniP vocab_sizer rr"r#(num_hidden_layers num_attention_headsrNnum_key_value_headsrrimax_position_embeddingsr$r%rrT use_cacherrrope_parameters pad_token_idc ^|j|j|_t| di|y)Nr3)rLrKsuper __post_init__selfkwargs __class__s r5rSzGlm4vTextConfig.__post_init__zs-  # # +'+'?'?D $ ''r4)!r&r'r(r)r*r+keys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planignore_keys_at_rope_validationrGr,r-rr#rIrKrLrr.rMr%r0rrNr/rrOrdictrPrS __classcell__rWs@r5r7r7Es- J#O#4"5&/%.%.%.%<"7 &(9:#%568IJ!"_$56 '6%6"JK"s"s!!&'t'J#(S(#u#L%It%(us{(48O^d*T18#L#*#((r4r7ceZdZUdZdZeedZdgZdZ e e zdze d<dZ e e zdze d<dZee d <d Zee d <d Zee d <dZee d<dZee d<dZee d<dZee d<fdZxZS) Glm4vConfiga image_start_token_id (`int`, *optional*, defaults to 151339): The image start token index to encode the start of image. image_end_token_id (`int`, *optional*, defaults to 151340): The image end token index to encode the end of image. video_start_token_id (`int`, *optional*, defaults to 151341): The video start token index to encode the start of video. video_end_token_id (`int`, *optional*, defaults to 151342): The video end token index to encode the end of video. ```python >>> from transformers import Glm4vForConditionalGeneration, Glm4vConfig >>> # Initializing a GLM-4.1V style configuration >>> configuration = Glm4vConfig() >>> # Initializing a model from the GLM-4.1V style configuration >>> model = Glm4vForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```glm4v)r r9r:Nr9r i/Oimage_token_idi0Ovideo_token_idi+Oimage_start_token_idi,Oimage_end_token_idi-Ovideo_start_token_idi.Ovideo_end_token_idFtie_word_embeddingsc t|jtr%|jddi|j|_n&|j|jddi||_t|jtr%|jddi|j|_n&|j|jddi||_t |di|y)Nr r9r3) isinstancer r\ sub_configsr9rRrSrTs r5rSzGlm4vConfig.__post_init__s d(($ /!B!1!1/!B!XTEWEW!XD     '!B!1!1/!B!LV!LD  d&& ->t// >RAQAQRD     %>t// >HHD  ''r4)r&r'r(r)r*r r7rkrXr9r\rr-r rbr,rcrdrerfrgrhr/rSr]r^s@r5r`r`s .J$5oVK#4"526K((4/648M4**T18 NC  NC &#&$$ &#&$$ %% ( (r4r`)r`r7r N) huggingface_hub.dataclassesrconfiguration_utilsrmodeling_rope_utilsrutilsrr r7r`__all__r3r4r5rqs(/31#9:%$(%$;%$P9:7(&7(;7(t9:1("1(;1(h Br4