| |
| from transformers.configuration_utils import PretrainedConfig |
|
|
|
|
| class PicaConfig(PretrainedConfig): |
| model_type = "pica" |
| keys_to_ignore_at_inference = ["past_key_values"] |
| def __init__( |
| self, |
| vocab_size=262144, |
| hidden_size=1024, |
| intermediate_size=3072, |
| num_hidden_layers=28, |
| num_attention_heads=16, |
| num_key_value_heads=8, |
| hidden_act="silu", |
| initializer_range=0.02, |
| rms_norm_eps=1e-6, |
| use_cache=True, |
| pad_token_id=0, |
| bos_token_id=2, |
| eos_token_id=1, |
| tie_word_embeddings=False, |
| attention_bias=False, |
| attention_dropout=0.0, |
| mlp_bias=False, |
| head_dim=128, |
| **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 |
|
|
| |
| if num_key_value_heads is None: |
| num_key_value_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.attention_bias = attention_bias |
| self.attention_dropout = attention_dropout |
| self.mlp_bias = mlp_bias |
| self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads |
|
|
| 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, |
| ) |
|
|
|
|
| __all__ = ["PicaConfig"] |
