| from typing import Literal |
| from transformers import PretrainedConfig |
|
|
|
|
| class EmuConfig(PretrainedConfig): |
| _auto_class = "AutoConfig" |
|
|
| def __init__( |
| self, |
| vocab_size=32000, |
| hidden_size=4096, |
| intermediate_size=11008, |
| num_hidden_layers=32, |
| num_attention_heads=32, |
| hidden_act='silu', |
| max_position_embeddings=2048, |
| initializer_range=0.02, |
| rms_norm_eps=1e-06, |
| model_version: Literal["base", "chat"] = "base", |
| pad_token_id=0, |
| bos_token_id=1, |
| eos_token_id=2, |
| tie_word_embeddings=False, |
| use_cache=True, |
| pretraining_tp=1, |
| rope_theta=10000.0, |
| rope_scaling=None, |
| attention_bias=False, |
| attention_dropout=0.0, |
| **kwargs, |
| ): |
| self.hidden_size = hidden_size |
| self.intermediate_size = intermediate_size |
| self.num_attention_heads = num_attention_heads |
| self.max_position_embeddings = max_position_embeddings |
| self.rms_norm_eps = rms_norm_eps |
| self.initializer_range = initializer_range |
| self.vocab_size = vocab_size |
| self.num_hidden_layers = num_hidden_layers |
| self.hidden_act = hidden_act |
| self.model_version = model_version |
| self.use_cache = use_cache |
| self.pretraining_tp = pretraining_tp |
| self.use_cache = use_cache |
| self.rope_theta = rope_theta |
| self.rope_scaling = rope_scaling |
| self._rope_scaling_validation() |
| self.attention_bias = attention_bias |
| self.attention_dropout = attention_dropout |
| 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, |
| ) |
|
|
| def _rope_scaling_validation(self): |
| """ |
| Validate the `rope_scaling` configuration. |
| """ |
| if self.rope_scaling is None: |
| return |
|
|
| if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2: |
| raise ValueError( |
| "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, " |
| f"got {self.rope_scaling}" |
| ) |
| rope_scaling_type = self.rope_scaling.get("type", None) |
| rope_scaling_factor = self.rope_scaling.get("factor", None) |
| if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]: |
| raise ValueError( |
| f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}" |
| ) |
| if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0: |
| raise ValueError(f"`rope_scaling`'s factor field must be a float > 1, got {rope_scaling_factor}") |
