| from __future__ import annotations |
|
|
| from transformers import PretrainedConfig |
|
|
|
|
| class TalkieConfig(PretrainedConfig): |
| model_type = "talkie" |
|
|
| def __init__( |
| self, |
| vocab_size: int = 65536, |
| n_layer: int = 40, |
| n_head: int = 40, |
| n_embd: int = 5120, |
| head_dim: int = 128, |
| max_position_embeddings: int = 2048, |
| rope_base: int = 1_000_000, |
| logit_scale: float = 1.0, |
| use_cache: bool = True, |
| tie_word_embeddings: bool = False, |
| bos_token_id: int | None = None, |
| eos_token_id: int | list[int] = 65535, |
| pad_token_id: int | None = None, |
| **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.n_layer = n_layer |
| self.n_head = n_head |
| self.n_embd = n_embd |
| self.head_dim = head_dim |
| self.max_position_embeddings = max_position_embeddings |
| self.rope_base = rope_base |
| self.logit_scale = logit_scale |
| self.use_cache = use_cache |
|
|
| |
| self.hidden_size = n_embd |
| self.num_hidden_layers = n_layer |
| self.num_attention_heads = n_head |
|
|
