.`i>&dZddlmZmZddlmZddlmZddlm Z e j e Z ddiZ eGdd ZeGd d ZGd d eZdS)zArctic model configuration)asdict dataclass)Any)PretrainedConfig)loggingarcticzPhttps://huggingface.co/Snowflake/snowflake-arctic-instruct/tree/main/config.jsonc:eZdZUdZeed<dZeed<dZe ed<dS)ArcticLoRAConfig@lora_r lora_alphaFshard_base_weightsN) __name__ __module__ __qualname__r int__annotations__rfloatrboolz/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/vllm/transformers_utils/configs/arctic.pyr r sCFCJ$$$$$$rr cHeZdZUdZeed<dZeed<dZeed<dZ eed<d S) ArcticQuantizationConfigq_bitsnearestrounding mantissa_bits group_sizeN) rrrrrrrstrr!r#rrrrrsOFCOOOHcM3JrrceZdZdZdZdgZ ddeeefdzffd Z e deeefddffd Z deeefffd Z xZ S) 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 ```rpast_key_values}8 Nsilu{Gz?h㈵>TFrMbP?rrope_parametersc 2||_||_||_||_||_||_||_||}||_||_| |_ | |_ | |_ | dd}|d|d}||_ ||_||_||_||_||_||_||_||_||_||_||_t3|t4rt7di||_n||_t;jd| | ||d|dS)N rope_thetag.Adefault) rope_typer5) pad_token_id bos_token_id eos_token_idtie_word_embeddingsr) vocab_sizemax_position_embeddings hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headssliding_windownum_key_value_heads hidden_actinitializer_range rms_norm_eps use_cachepopr3attention_dropoutnum_experts_per_toknum_local_expertsrouter_aux_loss_coefmoe_layer_frequencymoe_train_capacity_factormoe_eval_capacity_factor enable_expert_tensor_parallelismmoe_min_capacitymoe_token_droppingparallel_attn_mlp_res isinstancedictr quantizationsuper__init__)!selfr<r>r?r@rArCrDr=rErFrGr8r9r:r;r3rBrIrJrKrLrMrSrNrOrPrQrRrVkwargsr5 __class__s! rrXzArcticConfig.__init__}soB%'>$&!2!2#6 ,  &"5 #6 $!2("ZZ c22  ",5ZPPO.!2#6 !2$8!#6 )B&(@%0P- 0"4%:" lD ) ) - 8 H H< H HD   ,D  %%% 3         r config_dictreturnc tj|fi|}t|tr|dn|}t|jt rt di|j|_|S)Nrr)rW from_dictrTtuplerVrUr)clsr\rZresultconfigr[s rr_zArcticConfig.from_dictsq"";99&99(77CV f)4 0 0 R":"Q"QV=P"Q"QF  rct}t|dtrt |d|d<|S)NrV)rWto_dictrTrr)rYretr[s rrezArcticConfig.to_dictsJggoo c.)+C D D >"(^)<"="=C  r)r(r)r*r+r+Nr,r)r-r.TNr/r0FNNr1r/rr2r0Fr/r/FrTN)rrr__doc__ model_typekeys_to_ignore_at_inferencerUr$rrX classmethodr_re __classcell__)r[s@rr&r&&sEQ Q fJ#4"5  $!15"#"#!").=M M "c3h$.#M M M M M M ^DcN[c3hrr&N)rg dataclassesrrtypingr transformers.configuration_utilsrtransformers.utilsr get_loggerrlogger$ARCTIC_PRETRAINED_CONFIG_ARCHIVE_MAPr rr&rrrrss$! ))))))))======&&&&&&  H % % `($  %%%%%%% %   rrrrr#rrrrrr