rh8ddlmZddlmZGddeZdgZy))Optional)PretrainedConfigc/eZdZdZdZdgZ ddededededed ed ed ed ed ededededededededededede e ede e e f,fd Z xZ S) Lfm2Configa{ This is the configuration class to store the configuration of a [`Lfm2Model`]. It is used to instantiate a LFM2 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 LFM2-1.2B model. e.g. [LiquidAI/LFM2-1.2B](https://huggingface.co/LiquidAI/LFM2-1.2B) 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 65536): Vocabulary size of the LLaMA model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Lfm2Model`] hidden_size (`int`, *optional*, defaults to 2560): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 12288): 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*, defaults to 8): 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 128000): The maximum sequence length that this model might ever be used with. Lfm2 1 supports up to 2048 tokens, Lfm2 2 up to 4096, CodeLfm2 up to 16384. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. 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 0): Padding token id. bos_token_id (`int`, *optional*, defaults to 1): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 2): End of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `True`): Whether to tie weight embeddings rope_theta (`float`, *optional*, defaults to 1000000.0): The base period of the RoPE embeddings. conv_bias (`bool`, *optional*, defaults to `False`): Whether to use bias in the conv layers. conv_L_cache (`int`, *optional*, defaults to 3): L_cache dim in the conv layers. block_multiple_of (`int`, *optional*, defaults to 256): Multiple for the `intermediate_size`. block_ffn_dim_multiplier (`float`, *optional*, defaults to 1.0): Multiplier for the `intermediate_size`. block_auto_adjust_ff_dim (`bool`, *optional*, defaults to `True`): Whether to adjust the dim of the `intermediate_size`. full_attn_idxs (`Optional`, *optional*): Index of the layers which use attention. layer_types (`Optional`, *optional*): Type of each layers. ```python >>> from transformers import Lfm2Model, Lfm2Config >>> # Initializing a LFM2 model >>> configuration = Lfm2Config() >>> # Initializing a model from the LFM2-1.2B style configuration >>> model = Lfm2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```lfm2past_key_values vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_headsmax_position_embeddingsinitializer_rangenorm_eps use_cache pad_token_id bos_token_id eos_token_idtie_word_embeddings rope_theta conv_bias conv_L_cacheblock_multiple_ofblock_ffn_dim_multiplierblock_auto_adjust_ff_dimfull_attn_idxs layer_typesc ||_||_||_|jd||_||_| |_| |_||_||_ ||_ ||_ ||_ |jd||_ ||_||_||_||_|j"<||nt%t'|}t'|Dcgc] }||vrdnd c}|_|jd|}t)|Td| | | |d|ycc}w)Ntheta block_ff_dimfull_attentionconv tie_embedding)rrrr)r r r getrrrrrrrrrr rrrrlistrangesuper__init__)selfr r r r rrrrrrrrrrrrrrrrrrkwargsi __class__s ~/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/lfm2/configuration_lfm2.pyr+zLfm2Config.__init__es04%&!2 **Wj9'>$"  !2$7 #6 #("(NTrTg.AFrg?TNN)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferenceintfloatboolrr(strr+ __classcell__)r/s@r0rrsTL \J#4"5 !&!##%#$'.#'!$(%!$*-)-.2+//= = =  =  = ! = != "%= != = = = = = "= != "#= $%= &'= (#()= *#'+= ,!c+-= .d3i(/= = rN)typingrconfiguration_utilsrr__all__r&rAr0rEs&3O !O d .rA