o ¾e¦i×ã@sLdZddlmZddlmZddlmZe e¡Z Gdd„deƒZ dgZ dS)zPersimmon model configurationé)ÚPreTrainedConfig)ÚRopeParameters)Úloggingc&sîeZdZdZdZdgZ            d&dedBdedBdedBdedBdedBdedBdedBdedBdedBde dBde dBde e ee fBdBde dBdedBd edBd!edBd"edBd#edBf$‡fd$d%„ Z ‡Z S)'ÚPersimmonConfigaÉ This is the configuration class to store the configuration of a [`PersimmonModel`]. It is used to instantiate an Persimmon 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 [adept/persimmon-8b-base](https://huggingface.co/adept/persimmon-8b-base). 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 262144): Vocabulary size of the Persimmon model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`PersimmonModel`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 16384): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 36): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 64): Number of attention heads for each attention layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"relu2"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 16384): 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. layer_norm_eps (`float`, *optional*, defaults to 1e-5): 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`. 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`. qk_layernorm (`bool`, *optional*, default to `True`): Whether or not to normalize the Queries and Keys after projecting the hidden states hidden_dropout (`float`, *optional*, default to 0.0): The dropout ratio after applying the MLP to the hidden states. attention_dropout (`float`, *optional*, default to 0.0): The dropout ratio after computing the attention scores. Example: ```python >>> from transformers import PersimmonModel, PersimmonConfig >>> # Initializing a Persimmon persimmon-7b style configuration >>> configuration = PersimmonConfig() ```Ú persimmonÚpast_key_valuesééé@é$é@Úrelu2ç{®Gáz”?çñh㈵øä>TFNçééÚ vocab_sizeÚ hidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚ hidden_actÚmax_position_embeddingsÚinitializer_rangeÚlayer_norm_epsÚ use_cacheÚtie_word_embeddingsÚrope_parametersÚ qk_layernormÚhidden_dropoutÚattention_dropoutÚ pad_token_idÚ bos_token_idÚ eos_token_idc sŽ||_||_||_||_||_||_||_||_| |_| |_ | |_ ||_ ||_ | |_ | dd¡| |_||_||_||_tƒjdi|¤ŽdS)NÚpartial_rotary_factorgà?©)rrrrrrrrrrrr r!rÚ setdefaultrr"r#r$ÚsuperÚ__init__)Úselfrrrrrrrrrrrrrr r!r"r#r$Úkwargs©Ú __class__r&ús/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/persimmon/configuration_persimmon.pyr)Ss( zPersimmonConfig.__init__)rr r r r r r rrTFNTrrNrr)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚkeys_to_ignore_at_inferenceÚintÚstrÚfloatÚboolrÚdictr)Ú __classcell__r&r&r,r.rsv7íþýüûúùø ÷ ö õ ô óòñðïîírN) r2Úconfiguration_utilsrÚmodeling_rope_utilsrÚutilsrÚ get_loggerr/ÚloggerrÚ__all__r&r&r&r.Ús     h