o Û¾i>&ã@s‚dZddlmZmZddlmZddlmZddlm Z e   e ¡Z ddiZ eGdd „d ƒƒZeGd d „d ƒƒZGd d „d eƒZdS)zArctic model configurationé)ÚasdictÚ dataclass)ÚAny)ÚPretrainedConfig)ÚloggingÚarcticzPhttps://huggingface.co/Snowflake/snowflake-arctic-instruct/tree/main/config.jsonc@s2eZdZUdZeed<dZeed<dZe ed<dS)ÚArcticLoRAConfigé@Úlora_réÚ lora_alphaFÚshard_base_weightsN) Ú__name__Ú __module__Ú __qualname__r ÚintÚ__annotations__r Úfloatr Úbool©rrúZ/home/ubuntu/.local/lib/python3.10/site-packages/vllm/transformers_utils/configs/arctic.pyrs  rc@s>eZdZUdZeed<dZeed<dZeed<dZ eed<d S) ÚArcticQuantizationConfigéÚq_bitsÚnearestÚroundingéÚ mantissa_bitsé€Ú group_sizeN) rrrrrrrÚstrrrrrrrrs   rcs´eZdZdZdZdgZ                    ddeeefdBf‡fdd„ Z e deeefddf‡fdd„ ƒZ deeeff‡fdd„ Z ‡Z S)Ú ArcticConfigaY This is the configuration class to store the configuration of a [`ArcticModel`]. It is used to instantiate an Arctic 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 #TODO(rsamdani): add what model has the default config.. 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 32000): Vocabulary size of the Arctic model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ArcticModel`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 14336): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 32): Number of attention heads for each attention layer in the Transformer encoder. 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 checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `8`. 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 `4096*32`): The maximum sequence length that this model might ever be used with. Arctic's sliding window attention allows sequence of up to 4096*32 tokens. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rms_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*): The id of the padding token. bos_token_id (`int`, *optional*, defaults to 1): The id of the "beginning-of-sequence" token. eos_token_id (`int`, *optional*, defaults to 2): The id of the "end-of-sequence" token. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether the model's input and output word embeddings should be tied. rope_parameters (`dict`, *optional*): Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value accordingly. Expected contents: `rope_theta` (`float`): The base period of the RoPE embeddings. `rope_type` (`str`): The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope', 'llama3'], with 'default' being the original RoPE implementation. sliding_window (`int`, *optional*): Sliding window attention window size. If not specified, will default to `4096`. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. num_experts_per_tok (`int`, *optional*, defaults to 2): The number of experts to root per-token, can be also interpreted as the `top-p` routing parameter num_local_experts (`int`, *optional*, defaults to 8): Number of experts per Sparse MLP layer. router_aux_loss_coef (`float`, *optional*, defaults to 0.001): The aux loss factor for the total loss. ```python >>> from transformers import ArcticModel, ArcticConfig >>> # Initializing a Arctic 7B style configuration TODO(rsamdani): verify which model does the default configuration correspond to. >>> configuration = ArcticConfig() >>> # Initializing a model from the Arctic 7B style configuration >>> model = ArcticModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```rÚpast_key_valuesé}éé8é NÚsiluç{®Gáz”?çñh㈵øä>TééFçrçü©ñÒMbP?rÚrope_parametersc  sü||_||_||_||_||_||_||_|dur|}||_||_| |_ | |_ | |_ |  dd¡}|dur9d|dœ}||_ ||_||_||_||_||_||_||_||_||_||_||_t|tƒrktdi|¤Ž|_n||_tƒjd| | ||dœ|¤ŽdS)NÚ rope_thetag€„.AÚdefault)Ú rope_typer/)Ú pad_token_idÚ bos_token_idÚ eos_token_idÚtie_word_embeddingsr)Ú vocab_sizeÚmax_position_embeddingsÚ hidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚsliding_windowÚnum_key_value_headsÚ hidden_actÚinitializer_rangeÚ rms_norm_epsÚ use_cacheÚpopr.Úattention_dropoutÚnum_experts_per_tokÚnum_local_expertsÚrouter_aux_loss_coefÚmoe_layer_frequencyÚmoe_train_capacity_factorÚmoe_eval_capacity_factorÚ enable_expert_tensor_parallelismÚmoe_min_capacityÚmoe_token_droppingÚparallel_attn_mlp_resÚ isinstanceÚdictrÚ quantizationÚsuperÚ__init__) Úselfr6r8r9r:r;r=r>r7r?r@rAr2r3r4r5r.r<rCrDrErFrGrMrHrIrJrKrLrPÚkwargsr/©Ú __class__rrrR}sP!   ü ûzArcticConfig.__init__Ú config_dictÚreturnc sLtƒj|fi|¤Ž}t|tƒr|dn|}t|jtƒr$tdi|j¤Ž|_|S)Nrr)rQÚ from_dictrNÚtuplerPrOr)ÚclsrWrTÚresultÚconfigrUrrrYÌs  zArcticConfig.from_dictcs,tƒ ¡}t|dtƒrt|dƒ|d<|S)NrP)rQÚto_dictrNrr)rSÚretrUrrr^Ôs zArcticConfig.to_dict)r#r$r%r&r&Nr'r$r(r)TNr*r+FNNr,r*rr-r+Fr*r*FrTN)rrrÚ__doc__Ú model_typeÚkeys_to_ignore_at_inferencerOr rrRÚ classmethodrYr^Ú __classcell__rrrUrr!&sNSâïO "r!N)r`Ú dataclassesrrÚtypingrÚ transformers.configuration_utilsrÚtransformers.utilsrÚ get_loggerrÚloggerÚ$ARCTIC_PRETRAINED_CONFIG_ARCHIVE_MAPrrr!rrrrÚs    ÿ