a hV6@s2ddlmZddlmZGdddeZdgZdS))PretrainedConfig)rope_config_validationcsxeZdZdZdZdgZddddddddddddddddd Zd gd gfd d gd gfd gd gfdZd!fdd ZZ S)" DogeConfiga This is the configuration class to store the configuration of a [`DogeModel`]. It is used to instantiate an Doge model according to the specified arguments, defining the model architecture like [SmallDoge/Doge-320M](https://huggingface.co/SmallDoge/Doge-320M). 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 32768): Vocabulary size of the Doge2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`DogeModel`] hidden_size (`int`, *optional*, defaults to 1024): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 2048): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer decoder. hidden_dropout (`float`, *optional*, defaults to 0.0): Dropout probability for each sequence transformation and state transformation module. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. 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`. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether the model's input and output word embeddings should be tied. max_position_embeddings (`int`, *optional*, defaults to 2048): The maximum sequence length that this model might ever be used with. rope_theta (`float`, *optional*, defaults to 10000.0): The base period of the RoPE embeddings. rope_scaling (`Dict`, *optional*): Dictionary containing the scaling configuration for the RoPE embeddings. 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. Doge family of small models use `{ 'rope_type': 'dynamic', 'factor': 4.0, 'original_max_position_embeddings': 2048 }` as the default value. 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 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*): 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 `num_attention_heads`. 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. mlp_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers. sliding_window (`int`, *optional*): Sliding window attention window size. If not specified, will default to `None`. keep_window_size (`int`, *optional*, defaults to 2048): The window size of tokens that are not dynamically masked, and dynamic masking is only performed when the sequence length exceeds this value. is_moe (`bool`, *optional*, defaults to `False`): Whether to use the Cross Domain Mixture of Experts, if `True`, the MoE will inherit the MLP to initialize. num_experts (`int`, *optional*, defaults to 16384): Number of routed experts in the model. This is only used when `is_moe=True`. num_experts_per_tok (`int`, *optional*, defaults to 64): Number of selected experts to route per-token. norm_topk_prob (`bool`, *optional*, defaults to `False`): Whether to normalize the topk probabilities. output_router_logits (`bool`, *optional*, defaults to `False`): Whether or not the router logits should be returned by the model. Enabling this will also allow the model to output the auxiliary loss, including load balancing loss and router z-loss. router_aux_loss_coef (`float`, *optional*, defaults to 0.001): The aux loss factor for the total loss. ```python >>> from transformers import DogeConfig, DogeModel >>> # Initializing a Doge-320M style configuration >>> configuration = DogeConfig() >>> # Initializing a model from the Doge-320M style configuration >>> model = DogeModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ZdogeZpast_key_valuesZcolwiseZrowwiseZsequence_parallelZ colwise_repZ rowwise_rep)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.dt_projzlayers.*.self_attn.o_projzlayers.*.input_layernorm.weightzlayers.*.input_residual.weightz(layers.*.post_attention_layernorm.weightz'layers.*.post_attention_residual.weightz norm.weightzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projzlayers.*.mlp.router_gatezlayers.*.mlp.down_embedzlayers.*.mlp.up_embedZ input_idsZ inputs_embedsZ hidden_statesZattention_mask)Z embed_tokensZlayersZnorm silu{Gz?ư>TF@N@@MbP?c s||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ ||_ ||_ ||_||_||_||_||_||_||_||_||_||_||_|j durd|j vr|j d|j d<t||dur||_ tjfd| i|dS)NtypeZ rope_typetie_word_embeddings) vocab_size hidden_sizeintermediate_sizenum_hidden_layershidden_dropout hidden_actinitializer_range rms_norm_eps use_cachemax_position_embeddings rope_theta rope_scalingnum_attention_headsnum_key_value_headsattention_biasattention_dropoutmlp_biassliding_windowkeep_window_sizeis_moe num_expertsnum_experts_per_toknorm_topk_proboutput_router_logitsrouter_aux_loss_coefrsuper__init__)selfrrrrrrrrrrrrrr r!r"r#r$r%r&r'r(r)r*r+r,kwargs __class__g/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/doge/configuration_doge.pyr.sF zDogeConfig.__init__)rrrrr r r r TFrr NrNFr FNrFrrFFr) __name__ __module__ __qualname____doc__Z model_typeZkeys_to_ignore_at_inferenceZbase_model_tp_planZbase_model_pp_planr. __classcell__r3r3r1r4rsfp   rN)Zconfiguration_utilsrZmodeling_rope_utilsrr__all__r3r3r3r4s  W