o Zh;D@s~ddlmZmZmZmZddlmZddlmZddl m Z ddl m Z e eZGdd d eZGd d d eZd d gZd S) )AnyDictOptionalUnion)PretrainedConfig)rope_config_validation)logging)SiglipVisionConfigcseZdZdZdZdgZddddddddZdgdgfd d gd gfd gd gfd Z                       ! "d%fd#d$ ZZ S)&Gemma3TextConfiga! This is the configuration class to store the configuration of a [`Gemma3TextModel`]. It is used to instantiate an Gemma3Text model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Gemma3Text-7B. e.g. [google/gemma3_text-7b](https://huggingface.co/google/gemma3_text-7b) 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 262208): Vocabulary size of the Gemma3Text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Gemma3TextModel`] hidden_size (`int`, *optional*, defaults to 2304): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 9216): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 26): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*, defaults to 4): 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://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `num_attention_heads`. head_dim (`int`, *optional*, defaults to 256): The attention head dimension. hidden_activation (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`): The non-linear activation function (function or string) in the decoder. Will default to `"gelu_pytorch_tanh"` if not specified. `"gelu_pytorch_tanh"` uses an approximation of the `"gelu"` activation function. max_position_embeddings (`int`, *optional*, defaults to 131072): 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-06): 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`. pad_token_id (`int`, *optional*, defaults to 0): Padding token id. eos_token_id (`int`, *optional*, defaults to 1): End of stream token id. bos_token_id (`int`, *optional*, defaults to 2): Beginning of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `True`): Whether to tie weight embeddings rope_theta (`float`, *optional*, defaults to 1000000.0): The base period of the RoPE embeddings. attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`): Whether to use a bias in the query, key, value and output projection layers during self-attention. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. query_pre_attn_scalar (`float`, *optional*, defaults to 256): Scaling factor used on the attention scores sliding_window (`int`, *optional*, defaults to 4096): in Gemma3Text, every other layer uses sliding window attention. This is the size of the sliding window. 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. cache_implementation (`str`, *optional*, defaults to `"hybrid"`): the cache type to be used with `generate`. rope_scaling (`Dict`, *optional*): Dictionary containing the scaling configuration for the RoPE embeddings used in global attention. NOTE: if you apply new rope type and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value accordingly. Expected contents: `rope_type` (`str`): The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope', 'llama3'], with 'default' being the original RoPE implementation. `factor` (`float`, *optional*): Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In most scaling types, a `factor` of x will enable the model to handle sequences of length x * original maximum pre-trained length. `original_max_position_embeddings` (`int`, *optional*): Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during pretraining. `attention_factor` (`float`, *optional*): Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention computation. If unspecified, it defaults to value recommended by the implementation, using the `factor` field to infer the suggested value. `beta_fast` (`float`, *optional*): Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear ramp function. If unspecified, it defaults to 32. `beta_slow` (`float`, *optional*): Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear ramp function. If unspecified, it defaults to 1. `short_factor` (`List[float]`, *optional*): Only used with 'longrope'. The scaling factor to be applied to short contexts (< `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2 `long_factor` (`List[float]`, *optional*): Only used with 'longrope'. The scaling factor to be applied to long contexts (< `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2 `low_freq_factor` (`float`, *optional*): Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE `high_freq_factor` (`float`, *optional*): Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE rope_local_base_freq (float, *optional*, defaults to 10000.0): The base period of the RoPE embeddings for local attention. sliding_window_pattern (`int`, *optional*, defaults to 6): Pattern for the sliding window attention. ```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 ``` rope_local_base_freq (float, *optional*, defaults to 10000.0): The base period of the RoPE embeddings for local attention. sliding_window_pattern (`int`, *optional*, defaults to 6): Pattern for the sliding window attention. Z gemma3_textZpast_key_valuesZcolwiseZrowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projZ input_idsZ inputs_embedsZ hidden_statesZattention_mask)Z embed_tokensZlayersZnorm@ $gelu_pytorch_tanh{Gz?ư>Trr .AFNhybrid@c stjd| |||d|||_| |_||_||_||_||_||_||_ | |_ | |_ | |_ ||_ ||_||_||_||_||_||_||_||_||_||_||_t|dS)N) pad_token_id bos_token_id eos_token_idtie_word_embeddings)super__init__ vocab_sizemax_position_embeddings hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headshead_dimnum_key_value_headsinitializer_range rms_norm_eps use_cache rope_thetaattention_biasattention_dropouthidden_activationquery_pre_attn_scalarsliding_windowfinal_logit_softcappingattn_logit_softcappingcache_implementationrope_local_base_freqsliding_window_pattern rope_scalingr)selfr&r(r)r*r+r-r,r4r'r.r/r0rr!r r"r1r2r3r5r6r7r8r9r<r:r;kwargs __class__r#^/var/www/auris/lib/python3.10/site-packages/transformers/models/gemma3/configuration_gemma3.pyr%s@ zGemma3TextConfig.__init__)r rrrrrrrrrrTrrr TrFrrrNNrNrr) __name__ __module__ __qualname____doc__ model_typeZkeys_to_ignore_at_inferenceZbase_model_tp_planZbase_model_pp_planr% __classcell__r#r#r?rAr !sXy  r cseZdZdZdZddddZeedZ   dde e ee e e ffde e ee e e ffdededededeffdd ZZS) Gemma3Configa This is the configuration class to store the configuration of a [`Gemma3ForConditionalGeneration`]. It is used to instantiate an Gemma3ForConditionalGeneration according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the PaliGemma-2B. e.g. [google/gemma-3-4b](https://huggingface.co/google/gemma-3-4b) 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[Gemma3TextConfig, dict]`, *optional*): The config object of the text backbone. vision_config (`Union[AutoConfig, dict]`, *optional*): Custom vision config or dict. 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. image_token_index (`int`, *optional*, defaults to 262144): The image token index to encode the image prompt. 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 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 ```Zgemma3image_token_indexboi_token_indexeoi_token_index)Zimage_token_idZ boi_token_idZ eoi_token_id) text_config vision_configNrrrLrMmm_tokens_per_imager.c  s|dur t}tdn t|trtdi|}t|tr&tdi|}n |dur2t}td||_||_||_||_ ||_ ||_ ||_ t jdi|dS)Nz@text_config is None, using default Gemma3TextConfig text config.zFvision_config is None, using default SiglipVisionConfig vision config.r#)r loggerinfo isinstancedictr rLrMrQrJrKrIr.r$r%) r=rLrMrQrJrKrIr.r>r?r#rAr%*s$     zGemma3Config.__init__)NNrrNrOrPr)rBrCrDrErFZ attribute_mapr r Z sub_configsrrrstrrintfloatr%rGr#r#r?rArHs@0rHN)typingrrrrZconfiguration_utilsrZmodeling_rope_utilsrutilsr Zsiglipr Z get_loggerrBrRr rH__all__r#r#r#rAs     N ^