| | |
| | |
| |
|
| | from transformers.utils import logging |
| | from transformers.configuration_utils import PretrainedConfig |
| |
|
| |
|
| | logger = logging.get_logger(__name__) |
| |
|
| |
|
| | class PanguEmbeddedConfig(PretrainedConfig): |
| |
|
| | model_type = "PanguEmbedded" |
| | _auto_class = "AutoConfig" |
| |
|
| | def __init__( |
| | self, |
| | vocab_size=153376, |
| | hidden_size=4096, |
| | intermediate_size=12800, |
| | num_hidden_layers=34, |
| | num_attention_heads=32, |
| | num_key_value_heads=8, |
| | hidden_act="silu", |
| | max_position_embeddings=147456, |
| | initializer_range=0.02, |
| | rms_norm_eps=1e-5, |
| | use_cache=True, |
| | pad_token_id=0, |
| | bos_token_id=1, |
| | eos_token_id=45892, |
| | tie_word_embeddings=False, |
| | rope_theta=16000000.0, |
| | bias=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_hidden_layers = num_hidden_layers |
| | self.num_attention_heads = num_attention_heads |
| | self.num_key_value_heads = num_key_value_heads |
| | self.hidden_act = hidden_act |
| | self.initializer_range = initializer_range |
| | self.rms_norm_eps = rms_norm_eps |
| | self.use_cache = use_cache |
| | self.rope_theta = rope_theta |
| | self.bias = bias |
| | 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, |
| | ) |
| |
|
