| from transformers.configuration_utils import PretrainedConfig |
|
|
|
|
| class TinyConfig(PretrainedConfig): |
| """ |
| Configuration class for TinyStories Transformer. |
| """ |
|
|
| model_type = "tiny" |
|
|
| def __init__( |
| self, |
| vocab_size=8000, |
| hidden_size=384, |
| intermediate_size=1024, |
| num_hidden_layers=8, |
| num_attention_heads=6, |
| max_position_embeddings=512, |
| rms_norm_eps=1e-5, |
| rope_theta=10000.0, |
| tie_word_embeddings=True, |
| bos_token_id=2, |
| eos_token_id=3, |
| pad_token_id=0, |
| initializer_range=0.02, |
| hidden_dropout=0.0, |
| attention_dropout=0.0, |
| **kwargs, |
| ): |
| super().__init__( |
| bos_token_id=bos_token_id, |
| eos_token_id=eos_token_id, |
| pad_token_id=pad_token_id, |
| tie_word_embeddings=tie_word_embeddings, |
| **kwargs, |
| ) |
|
|
| self.vocab_size = vocab_size |
|
|
| 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.max_position_embeddings = max_position_embeddings |
|
|
| self.rms_norm_eps = rms_norm_eps |
|
|
| self.rope_theta = rope_theta |
|
|
| self.initializer_range = initializer_range |
|
|
| self.hidden_dropout = hidden_dropout |
|
|
| self.attention_dropout = attention_dropout |
|
|
| @property |
| def head_dim(self): |
| return self.hidden_size // self.num_attention_heads |
