| from transformers.configuration_utils import PretrainedConfig | |
| class GPTPanguConfig(PretrainedConfig): | |
| model_type = "gpt_pangu" | |
| keys_to_ignore_at_inference = ["past_key_values"] | |
| def __init__( | |
| self, | |
| vocab_size=40000, | |
| max_position_embeddings=1024, | |
| hidden_size=5120, | |
| intermediate_size=None, | |
| num_layers=40, | |
| num_heads=40, | |
| activation_function="gelu", | |
| resid_pdrop=0.1, | |
| embd_pdrop=0.1, | |
| attn_pdrop=0.1, | |
| layer_norm_epsilon=1e-5, | |
| scale_attn_weights=True, | |
| initializer_range=0.02, | |
| summary_type="cls_index", | |
| summary_use_proj=True, | |
| summary_activation=None, | |
| summary_proj_to_labels=True, | |
| summary_first_dropout=0.1, | |
| use_cache=True, | |
| **kwargs, | |
| ): | |
| self.vocab_size = vocab_size | |
| self.max_position_embeddings = max_position_embeddings | |
| self.hidden_size = hidden_size | |
| self.intermediate_size = intermediate_size | |
| self.num_layers = num_layers | |
| self.num_heads = num_heads | |
| self.activation_function = activation_function | |
| self.resid_pdrop = resid_pdrop | |
| self.embd_pdrop = embd_pdrop | |
| self.attn_pdrop = attn_pdrop | |
| self.layer_norm_epsilon = layer_norm_epsilon | |
| self.scale_attn_weights = scale_attn_weights | |
| self.initializer_range = initializer_range | |
| self.summary_type = summary_type | |
| self.summary_use_proj = summary_use_proj | |
| self.summary_activation = summary_activation | |
| self.summary_first_dropout = summary_first_dropout | |
| self.summary_proj_to_labels = summary_proj_to_labels | |
| self.use_cache = use_cache | |
| super().__init__(**kwargs) | |