o ei@s2ddlmZddlmZGdddeZdgZdS))PretrainedConfig)RopeParametersc'seZdZdZdZdgZdddddddZ             d,dededed Bdededed Bdedede d e d!e d"e e Bd Bd#e d$e d Bd%e d&ed'ed(ed)e f&fd*d+ Z ZS)-NanoChatConfiga This is the configuration class to store the configuration of a [`NanoChatModel`]. It is used to instantiate a NanoChat 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 [karpathy/nanochat-d32](https://huggingface.co/karpathy/nanochat-d32). 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 NanoChat model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`NanoChatModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 8192): Dimension of the MLP representations. If `None`, it will be computed based on the model architecture. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 6): 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`. max_position_embeddings (`int`, *optional*, defaults to 2048): The maximum sequence length that this model might ever be used with. hidden_act (`str` or `function`, *optional*, defaults to `"relu2"`): The non-linear activation function (function or string) in the decoder. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. rms_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the rms normalization layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rope_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionaty 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`. 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`. final_logit_softcapping (`float`, *optional*, defaults to 15.0): scaling factor when applying tanh softcapping on the logits. attention_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in the query, key, and value projection layers during self-attention. bos_token_id (`int`, *optional*, defaults to 0): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 1): End of stream token id. pad_token_id (`int`, *optional*, defaults to 1): Padding token id. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings ```python >>> from transformers import NanoChatModel, NanoChatConfig >>> # Initializing a NanoChat style configuration >>> configuration = NanoChatConfig() >>> # Initializing a model from the NanoChat style configuration >>> model = NanoChatModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```nanochatpast_key_valuescolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.fc1zlayers.*.mlp.fc2 Nrelu2ư>{Gz?T.@F vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_headsmax_position_embeddings hidden_actattention_dropout rms_norm_epsinitializer_rangerope_parameters use_cachefinal_logit_softcappingattention_bias bos_token_id eos_token_id pad_token_idtie_word_embeddingsc s||_||_||_||_||_|dur|}||_||_||_| |_| |_ | |_ | |_ ||_ ||_ | |_||_||_||_||_tjdi|dS)N)rrrrrrrrrrr r"r#r$r!r'r%r&r(super__init__)selfrrrrrrrrrrr r!r"r#r$r%r&r'r(kwargs __class__r)q/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/nanochat/configuration_nanochat.pyr+hs,zNanoChatConfig.__init__)r r r r r NrrrrrNTrFrrrF)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencebase_model_tp_planintstrfloatrdictboolr+ __classcell__r)r)r.r0rsH      rN)configuration_utilsrmodeling_rope_utilsrr__all__r)r)r)r0s