o ¾e¦i¡ã@sLdZddlmZddlmZddlmZe e¡Z Gdd„deƒZ dgZ dS)zOLMo model configurationé)ÚPreTrainedConfig)ÚRopeParameters)Úloggingc&s(eZdZdZdZdgZddddddddœZdgdgfd d gd gfd gd gfd œZ                d-dedBdedBdedBdedBdedBdedBde dBd edBd!e dBd"e dBd#edBd$edBd%edBd&edBd'e e e e fBdBd(e dBd)e dBd*e dBf$‡fd+d,„ Z‡ZS).Ú OlmoConfiga This is the configuration class to store the configuration of a [`OlmoModel`]. It is used to instantiate an OLMo 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/OLMo-7B-hf](https://huggingface.co/allenai/OLMo-7B-hf). 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 OLMo model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`OlmoModel`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 11008): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 32): 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 2048): 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. 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. ```python >>> from transformers import OlmoModel, OlmoConfig >>> # Initializing a OLMo 7B style configuration >>> configuration = OlmoConfig() >>> # Initializing a model from the OLMo 7B style configuration >>> model = OlmoModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ÚolmoÚpast_key_valuesÚcolwiseÚrowwise)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_projÚ input_idsÚ inputs_embedsÚ hidden_statesÚattention_mask)Ú embed_tokensÚlayersÚnormé€Äéé+é NÚsiluéç{®Gáz”?TéégÄFçÚ vocab_sizeÚ hidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚnum_key_value_headsÚ hidden_actÚmax_position_embeddingsÚinitializer_rangeÚ use_cacheÚ pad_token_idÚ bos_token_idÚ eos_token_idÚtie_word_embeddingsÚrope_parametersÚattention_biasÚattention_dropoutÚclip_qkvc sŽ||_||_||_||_||_||_|dur|}||_||_| |_| |_ ||_ ||_ ||_ ||_ ||_| |_| |_| |_tƒjdi|¤ŽdS)N©)rr"rrrrr r!r#r$r*r+r,r)r(r%r&r'ÚsuperÚ__init__)Úselfrrrrrr r!r"r#r$r%r&r'r(r)r*r+r,Úkwargs©Ú __class__r-úi/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/olmo/configuration_olmo.pyr/vs*zOlmoConfig.__init__)rrrrrNrrrTrNrFNFrN)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planÚintÚstrÚfloatÚboolrÚdictr/Ú __classcell__r-r-r2r4rsŽGù  ýíþýüûúùø ÷ ö õ ô óòñðïîírN) r8Úconfiguration_utilsrÚmodeling_rope_utilsrÚutilsrÚ get_loggerr5ÚloggerrÚ__all__r-r-r-r4Ús