| from transformers import PretrainedConfig | |
| class DwarfConfig(PretrainedConfig): | |
| model_type = "dwarf" | |
| def __init__(self, vocab_size=8202, d_model=320, n_layers=12, n_heads=5, | |
| n_kv_heads=1, d_ff=864, max_seq_len=2048, rope_theta=10000.0, | |
| norm_eps=1e-5, head_dim=64, **kwargs): | |
| self.vocab_size = vocab_size | |
| self.d_model = d_model | |
| self.n_layers = n_layers | |
| self.n_heads = n_heads | |
| self.n_kv_heads = n_kv_heads | |
| self.d_ff = d_ff | |
| self.max_seq_len = max_seq_len | |
| self.rope_theta = rope_theta | |
| self.norm_eps = norm_eps | |
| self.head_dim = head_dim | |
| self.num_hidden_layers = n_layers | |
| self.hidden_size = d_model | |
| self.num_attention_heads = n_heads | |
| self.num_key_value_heads = n_kv_heads | |
| super().__init__(**kwargs) | |