| from transformers import PretrainedConfig | |
| class BigBrainConfig(PretrainedConfig): | |
| model_type = 'big-brain-lm' | |
| def __init__( | |
| self, | |
| vocab_size=50265, | |
| hidden_size=768, | |
| num_hidden_layers=12, | |
| num_attention_heads=12, | |
| intermediate_size=3072, | |
| hidden_act='gelu', | |
| hidden_dropout_probability=0.1, | |
| attention_probs_dropout_prob=0.1, | |
| max_position_embeddings=512, | |
| initializer_range=0.02, | |
| layer_norm_eps=1e-6, | |
| rope_theta=10000, | |
| sos_token_id=0, | |
| pad_token_id=1, | |
| eos_token_id=2, | |
| unk_token_id=3, | |
| **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_act = hidden_act | |
| self.hidden_dropout_probability = hidden_dropout_probability | |
| self.attention_probs_dropout_prob = attention_probs_dropout_prob | |
| self.max_position_embeddings = max_position_embeddings | |
| self.initializer_range = initializer_range | |
| self.layer_norm_eps = layer_norm_eps | |
| self.rope_theta = rope_theta | |
| self.sos_token_id = sos_token_id | |
| self.pad_token_id = pad_token_id | |
| self.eos_token_id = eos_token_id | |
| self.unk_token_id = unk_token_id | |
| super().__init__(**kwargs) | |