| """ | |
| Kayra Configuration | |
| """ | |
| from transformers import PretrainedConfig | |
| class KayraConfig(PretrainedConfig): | |
| model_type = "kayra" | |
| def __init__( | |
| self, | |
| vocab_size=32000, | |
| hidden_size=640, | |
| num_hidden_layers=10, | |
| num_attention_heads=10, | |
| intermediate_size=2560, | |
| hidden_dropout=0.1, | |
| attention_dropout=0.1, | |
| max_position_embeddings=512, | |
| initializer_range=0.02, | |
| use_cache=True, | |
| pad_token_id=0, | |
| bos_token_id=2, | |
| eos_token_id=3, | |
| tie_word_embeddings=True, | |
| **kwargs | |
| ): | |
| self.vocab_size = vocab_size | |
| self.hidden_size = hidden_size | |
| self.num_hidden_layers = num_hidden_layers | |
| self.num_attention_heads = num_attention_heads | |
| self.intermediate_size = intermediate_size | |
| self.hidden_dropout = hidden_dropout | |
| self.attention_dropout = attention_dropout | |
| self.max_position_embeddings = max_position_embeddings | |
| self.initializer_range = initializer_range | |
| self.use_cache = use_cache | |
| 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 | |
| ) | |