from transformers.configuration_utils import PretrainedConfig from transformers.utils import logging logger = logging.get_logger(__name__) VELTRAXOR_PRETRAINED_CONFIG_ARCHIVE_MAP = {} class VeltraxorConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek 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 DeepSeek-V3. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. """ model_type = "veltraxor" keys_to_ignore_at_inference = ["past_key_values"] def __init__( self, vocab_size=129280, hidden_size=7168, intermediate_size=18432, moe_intermediate_size=2048, num_hidden_layers=61, num_nextn_predict_layers=1, num_attention_heads=128, num_key_value_heads=128, n_shared_experts=1, n_routed_experts=256, ep_size=1, routed_scaling_factor=2.5, kv_lora_rank=512, q_lora_rank=1536, qk_rope_head_dim=64, v_head_dim=128, qk_nope_head_dim=128, topk_method='noaux_tc', n_group=8, topk_group=4, num_experts_per_tok=8, moe_layer_freq=1, first_k_dense_replace=3, norm_topk_prob=True, scoring_func='sigmoid', hidden_act="silu", max_position_embeddings=4096, initializer_range=0.02, rms_norm_eps=1e-6, use_cache=True, pad_token_id=None, bos_token_id=0, eos_token_id=1, tie_word_embeddings=False, rope_theta=10000.0, rope_scaling=None, attention_bias=False, attention_dropout=0.0, **kwargs, ): super().__init__( pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs, ) DeepseekV3Config = VeltraxorConfig