qi8ddlmZddlmZGddeZdgZy))PretrainedConfig)RopeParametersc'eZdZdZdZdgZdddddddZ dded ed edzd ed ed edzdedede de de de e zdzde de dzde dededede f&fd Z xZS)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.fc2N 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 6||_||_||_||_||_||}||_||_||_| |_| |_ | |_ | |_ ||_ ||_ | |_||_||_||_||_t'|Pdi|y)N)r r r rrrrrrrrrrrrrrrrsuper__init__)selfr r r rrrrrrrrrrrrrrrrkwargs __class__s e/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/nanochat/configuration_nanochat.pyr!zNanoChatConfig.__init__hs.%&!2!2#6   &"5 #6 '>$$!2(!2"'>$,.(((#6  "6")iii Nirelu2ggư>g{Gz?NTg.@Fr+F)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencebase_model_tp_planintstrfloatrdictboolr! __classcell__)r$s@r%rrsMF PJ#4"5&/%.%.%.%%  (,!##$*.'+!#&"#'8<04$$))0#0#0#: 0#  0# ! 0#!4Z0#"%0#0#!0#0#!0#($.50#0#"'0# !0#"#0#$%0#&'0#(")0#0#r&rN)configuration_utilsrmodeling_rope_utilsrr__all__rr&r%r<s'41E#%E#P  r&