""" Boomer model configuration""" from transformers.configuration_utils import PretrainedConfig from transformers.utils import logging logger = logging.get_logger(__name__) class BoomerConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`BoomerModel`]. It is used to instantiate an Boomer model according to the specified arguments, defining the model architecture. 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 51200): Vocabulary size of the Boomer model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`BoomerModel`]. hidden_size (`int`, *optional*, defaults to 2048): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 8192): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 24): 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*): 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. If it is not specified, will default to `num_attention_heads`. resid_pdrop (`float`, *optional*, defaults to 0.0): Dropout probability for mlp outputs. embd_pdrop (`int`, *optional*, defaults to 0.0): The dropout ratio for the embeddings. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio after computing the attention scores. hidden_act (`str` or `function`, *optional*, defaults to `"gelu_new"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 2048): The maximum sequence length that this model might support up to 2048 tokens. 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-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`. Whether to tie weight embeddings or not. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings rope_theta (`float`, *optional*, defaults to 10000.0): The base period of the RoPE embeddings. rope_scaling (`Dict`, *optional*): Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling strategies: linear and dynamic. Their scaling factor must be an float greater than 1. The expected format is `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update `max_position_embeddings` to the expected new maximum. partial_rotary_factor (`float`, *optional*, defaults to 0.5): Percentage of the query and keys which will have rotary embedding. qk_layernorm (`bool`, *optional*, defaults to `False`): Whether or not to normalize the Queries and Keys after projecting the hidden states. bos_token_id (`int`, *optional*, defaults to 1): Denotes beginning of sequences token id. eos_token_id (`int`, *optional*, defaults to 2): Denotes end of sequences token id. ```""" model_type = "Boomer" keys_to_ignore_at_inference = ["past_key_values"] def __init__( self, vocab_size=51200, hidden_size=2048, intermediate_size=8192, num_hidden_layers=24, num_attention_heads=32, num_key_value_heads=None, resid_pdrop=0.0, embd_pdrop=0.0, attention_dropout=0.0, hidden_act="gelu_new", max_position_embeddings=2048, initializer_range=0.02, layer_norm_eps=1e-5, use_cache=True, tie_word_embeddings=False, rope_theta=10000.0, rope_scaling=None, partial_rotary_factor=0.5, qk_layernorm=False, bos_token_id=1, eos_token_id=2, adapter_scaling=0.25, adapter_dim=512, **kwargs, ): self.vocab_size = vocab_size self.hidden_size = hidden_size self.intermediate_size = intermediate_size self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads if num_key_value_heads is None: num_key_value_heads = num_attention_heads self.num_key_value_heads = num_key_value_heads self.resid_pdrop = resid_pdrop self.embd_pdrop = embd_pdrop self.attention_dropout = attention_dropout self.hidden_act = hidden_act self.max_position_embeddings = max_position_embeddings self.initializer_range = initializer_range self.layer_norm_eps = layer_norm_eps self.use_cache = use_cache self.rope_theta = rope_theta self.rope_scaling = rope_scaling self.partial_rotary_factor = partial_rotary_factor self.qk_layernorm = qk_layernorm self._rope_scaling_validation() self.adapter_dim = adapter_dim self.adapter_scaling = adapter_scaling super().__init__( bos_token_id=bos_token_id, eos_token_id=eos_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs, ) # Copied from transformers.models.llama.configuration_llama.LlamaConfig._rope_scaling_validation def _rope_scaling_validation(self): """ Validate the `rope_scaling` configuration. """ if self.rope_scaling is None: return if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2: raise ValueError( "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, " f"got {self.rope_scaling}" ) rope_scaling_type = self.rope_scaling.get("type", None) rope_scaling_factor = self.rope_scaling.get("factor", None) if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]: raise ValueError( f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}" ) if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0: raise ValueError(f"`rope_scaling`'s factor field must be a float > 1, got {rope_scaling_factor}")