configuration_rapnss.py

from transformers import PretrainedConfig

class RapnssConfig(PretrainedConfig):
    model_type = "rapnss"
    
    def __init__(
        self,
        vocab_size=50257,
        d_model=768,
        n_heads=12,
        n_layers=12,
        d_ff=3072,
        max_seq_len=512,
        dropout=0.1,
        tie_word_embeddings=True,
        architectures=["RapnssForCausalLM"],
        **kwargs
    ):
        self.vocab_size = vocab_size
        self.d_model = d_model
        self.n_heads = n_heads
        self.n_layers = n_layers
        self.d_ff = d_ff
        self.max_seq_len = max_seq_len
        self.dropout = dropout
        super().__init__(**kwargs)
        self.is_decoder = True
        self.num_hidden_layers = n_layers