o ¾e¦i‚!ã@s6dZddlmZddlmZGdd„deƒZdgZdS)zOLMoE model configurationé)ÚPreTrainedConfig)ÚRopeParametersc2s2eZdZdZdZdgZddiZ                d/ded Bded Bded Bded Bded Bded Bded Bded Bde d Bded Bd e d Bd!ed Bd"ed Bd#ed Bd$ed Bd%e e ee fBd Bd&e d Bd'e d Bd(e d Bd)ed Bded Bd*e d Bd+e d Bd,e d Bf0‡fd-d.„ Z ‡ZS)0Ú OlmoeConfigas This is the configuration class to store the configuration of a [`OlmoeModel`]. It is used to instantiate an OLMoE 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 [allenai/OLMoE-1B-7B-0924](https://huggingface.co/allenai/OLMoE-1B-7B-0924). 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 50304): Vocabulary size of the OLMoE model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`OlmoeModel`] hidden_size (`int`, *optional*, defaults to 2048): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 2048): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 16): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 16): 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, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `num_attention_heads`. 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 4096): 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`. pad_token_id (`int`, *optional*, defaults to 1): Padding token id. bos_token_id (`int`, *optional*): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 50279): End of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings 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`. 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. clip_qkv (`float`, *optional*): If not `None`, elements of query, key and value attention states are clipped so that their absolute value does not exceed this value. num_experts_per_tok (`int`, *optional*, defaults to 8): Number of selected experts. num_experts (`int`, *optional*, defaults to 64): Number of routed experts. 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 0.01): The aux loss factor for the total loss. norm_topk_prob (`bool`, *optional*, defaults to `False`): Whether to normalize the topk probabilities. ```python >>> from transformers import OlmoeModel, OlmoeConfig >>> # Initializing a OLMoE 7B A1B style configuration >>> configuration = OlmoeConfig() >>> # Initializing a model from the OLMoE 7B A1B style configuration >>> model = OlmoeModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ÚolmoeÚpast_key_valuesÚnum_local_expertsÚ num_expertsé€ÄééNÚsiluéç{®Gáz”?çñh㈵øä>TéégÄFçéé@ç{®Gáz„?Ú vocab_sizeÚ hidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚnum_key_value_headsÚ hidden_actÚmax_position_embeddingsÚinitializer_rangeÚ rms_norm_epsÚ use_cacheÚ pad_token_idÚ bos_token_idÚ eos_token_idÚtie_word_embeddingsÚrope_parametersÚattention_biasÚattention_dropoutÚclip_qkvÚnum_experts_per_tokÚoutput_router_logitsÚrouter_aux_loss_coefÚnorm_topk_probc s²||_||_||_||_||_||_|dur|}||_||_| |_| |_ | |_ ||_ ||_ ||_ ||_||_||_||_||_||_||_| |_| |_||_tƒjdi|¤ŽdS)N©)rrrrrrrrrrr r&r'r(r)rr*r+r,r%r$r!r"r#ÚsuperÚ__init__)Úselfrrrrrrrrrrr r!r"r#r$r%r&r'r(r)rr*r+r,Úkwargs©Ú __class__r-úk/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/olmoe/configuration_olmoe.pyr/ks6zOlmoeConfig.__init__)r r r r r Nr r rrTrNrFNFrNrrFrF)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚkeys_to_ignore_at_inferenceÚ attribute_mapÚintÚstrÚfloatÚboolrÚdictr/Ú __classcell__r-r-r2r4rsœTçþýüûúùø ÷ ö õ ô óòñðïîíìëêéèçrN)r8Úconfiguration_utilsrÚmodeling_rope_utilsrrÚ__all__r-r-r-r4Ús