tj&ddlmZddlmZddlmZddlmZmZddl m Z ej e Z ed eGd d eZed eGd d eZd d gZdS))Any)strict)PreTrainedConfig)auto_docstringlogging)SiglipVisionConfigzgoogle/gemma-3-4b-it) checkpointc @eZdZUdZdZdgZdddddddddd Zdgd gfd d gd gfd gd gfd Zd Ze e d<dZ e e d<dZ e e d<dZ e e d<dZe e d<dZe e d<dZe e d<dZee d<dZe e d<dZee d <d!Zee d"<d#Zee d$<d%Ze d&ze d'<d(Ze ee zd&ze d)<d*Ze d&ze d+<d#Zee d,<d&Zed&ze d-<d.Z ee d/<d0Z!e ezd&ze d1<dZ"e e d2<d3Z#e d&ze d4<d&Z$eed&ze d5<d&Z%ed&ze d6<d&Z&ed&ze d7<d.Z'ed&ze d8<d9d:d;Z(fd<Z)d=Z*d>Z+xZ,S)?Gemma3TextConfiga query_pre_attn_scalar (`float`, *optional*, defaults to 256): scaling factor used on the attention scores final_logit_softcapping (`float`, *optional*): Scaling factor when applying tanh softcapping on the logits. attn_logit_softcapping (`float`, *optional*): Scaling factor when applying tanh softcapping on the attention scores. use_bidirectional_attention (`bool`, *optional*, defaults to `False`): If True, the model will attend to all text tokens instead of using a causal mask. This does not change behavior for vision tokens. ```python >>> from transformers import Gemma3TextModel, Gemma3TextConfig >>> # Initializing a Gemma3Text gemma3_text-7b style configuration >>> configuration = Gemma3TextConfig() >>> # Initializing a model from the gemma3_text-7b style configuration >>> model = Gemma3TextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` gemma3_textpast_key_valuescolwisereplicated_with_grad_allreducerowwise) zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.q_normzlayers.*.self_attn.k_normzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj input_ids inputs_embeds hidden_statesattention_mask) embed_tokenslayersnormi@ vocab_sizei hidden_sizei$intermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_headshead_dimgelu_pytorch_tanhhidden_activationimax_position_embeddings{Gz?initializer_rangegư> rms_norm_epsT use_cacherN pad_token_id eos_token_idr bos_token_idtie_word_embeddingsrope_parametersFattention_biasgattention_dropoutquery_pre_attn_scalarisliding_window layer_typesfinal_logit_softcappingattn_logit_softcappinguse_bidirectional_attentiong.Ag@)globallocalc jrjdzdz_|dd_j%fdt jD_tjdi|dS)Nr r-sliding_window_patterncLg|] }t|dzjzrdnd!S)r-sliding_attentionfull_attention)bool_sliding_window_pattern).0iselfs m/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/gemma3/configuration_gemma3.py z2Gemma3TextConfig.__post_init__..psI   (,QUd6R,R'S'Si##Yi   ) r9r5getrCr6rangersuper __post_init__rFkwargs __class__s` rGrNzGemma3TextConfig.__post_init__hs  + A#'#6!#;q"@D (.zz2JA'N'N$   #    t566   D  '''''''rIcl|j|jzdkr td|jd|jddS)zOPart 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).N)rr ValueError)rFs rGvalidate_architecturez&Gemma3TextConfig.validate_architecturews[  d6 6! ; ;7D$4772777  < ;rIc r|dd}ddiddid}|j|jn||_| |jd||jd ddi|jd<|jdd|d|jd|jd ddi|jd<|jdd|d |jd ||S) N rope_scaling rope_typedefault)r@rArA rope_thetar:r@rope_local_base_freqr;)popr1updaterK setdefault default_thetastandardize_rope_params)rFrPrVdefault_rope_paramss rGconvert_rope_params_to_dictz,Gemma3TextConfig.convert_rope_params_to_dicts_zz.$77 #.y!9*I6  8<7K7Wt33]p  #  !1 2 9 9, G G G   # #$4 5 5 =6A95MD !1 2 -.99 &**\43Eh3OPP      # #$7 8 8 @9Di8PD !4 5 01<< &**%;T=OPW=XYY   $$&&& rI)-__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planrint__annotations__rrrr r"r$r&strr'r)floatr*r+rBr,r.listr/r0r1dictr2r3r4r5r6r7r8r9r^rNrTra __classcell__rQs@rGr r !s,J#4"5%.%.%.%E%E%."+ )"+  &(9:#%568IJ!"_$56 JK!s!!!s        Hc0s000#*S***#u###L%It L#*   +,L#S /D(,,, L#*   $$$$#'OTD[''' ND   ,/sU{T)///!$3$$$!%NC$J%%%$(KcT!(((,0UT\000+/EDL////4444*X>>M ( ( ( ( (rIr c eZdZUdZdZddddZeedZdZ ee e e fzdze d <dZee e e fzdze d <d Zedze d <d Zedze d<dZedze d<dZedze d<dZedze d<dZedze d<fdZxZS) Gemma3Configa mm_tokens_per_image (`int`, *optional*, defaults to 256): The number of tokens per image embedding. boi_token_index (`int`, *optional*, defaults to 255999): The begin-of-image token index to wrap the image prompt. eoi_token_index (`int`, *optional*, defaults to 256000): The end-of-image token index to wrap the image prompt. Example: ```python >>> from transformers import Gemma3ForConditionalGeneration, Gemma3Config, SiglipVisionConfig, Gemma3TextConfig >>> # Initializing a Siglip-like vision config >>> vision_config = SiglipVisionConfig() >>> # Initializing a Gemma3 Text config >>> text_config = Gemma3TextConfig() >>> # Initializing a Gemma3 gemma-3-4b style configuration >>> configuration = Gemma3Config(vision_config, text_config) >>> # Initializing a model from the gemma-3-4b style configuration >>> model = Gemma3TextConfig(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```gemma3image_token_indexboi_token_indexeoi_token_index)image_token_id boi_token_id eoi_token_id) text_config vision_configNr{r|r#mm_tokens_per_imageiiir(r)Tr0c |j.t|_tdn0t |jt rtdi|j|_t |jt rtdi|j|_n4|j-t|_tdtj di|dS)Nz@text_config is None, using default Gemma3TextConfig text config.zFvision_config is None, using default SiglipVisionConfig vision config.rJ) r{r loggerinfo isinstanceror|r rMrNrOs rGrNzGemma3Config.__post_init__s   #/11D  KKZ [ [ [ [ ($ / / D/CC$2BCCD  d($ / / b!3!I!Id6H!I!ID     '!3!5!5D  KK` a a a'''''''rI)rbrcrdrerf attribute_mapr r sub_configsr{rorlrrkr|r}rjrvrwrur)rmr0rBrNrprqs@rGrsrss9  :J-))M (+K =AK!DcN2T9@@@@DM%S#X6=DDD&)t)))")OS4Z)))")OS4Z)))$+sTz+++&*ut|***'++++ ( ( ( ( ( ( ( ( (rIrsN)typingrhuggingface_hub.dataclassesrconfiguration_utilsrutilsrrsiglipr get_loggerrbrr rs__all__rJrIrGrs6*......333333,,,,,,,,''''''  H % %1222wwwww'ww32wt1222?(?(?(?(?(#?(?(32?(D - .rI