|
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
from typing import Any, Optional
|
|
|
from transformers import PretrainedConfig
|
|
|
|
|
|
|
|
|
class EveConfig(PretrainedConfig):
|
|
|
model_type = "eve_moe"
|
|
|
attribute_map = {
|
|
|
"num_hidden_layers": "n_layer",
|
|
|
"num_attention_heads": "n_head",
|
|
|
"hidden_size": "n_embd",
|
|
|
"max_position_embeddings": "block_size",
|
|
|
}
|
|
|
|
|
|
def __init__(
|
|
|
self,
|
|
|
vocab_size: int = 50304,
|
|
|
n_layer: int = 12,
|
|
|
n_embd: int = 512,
|
|
|
n_head: int = 8,
|
|
|
head_dim: int = 64,
|
|
|
block_size: int = 2048,
|
|
|
num_experts: int = 8,
|
|
|
top_k: int = 2,
|
|
|
expert_intermediate_size: int = 1408,
|
|
|
shared_expert_intermediate_size: int = 1408,
|
|
|
router_aux_loss_coef: float = 0.01,
|
|
|
use_checkpointing: bool = False,
|
|
|
rope_theta: float = 10000.0,
|
|
|
**kwargs: Any,
|
|
|
):
|
|
|
self.vocab_size = vocab_size
|
|
|
self.n_layer = n_layer
|
|
|
self.n_embd = n_embd
|
|
|
self.n_head = n_head
|
|
|
self.head_dim = head_dim
|
|
|
self.block_size = block_size
|
|
|
self.num_experts = num_experts
|
|
|
self.top_k = top_k
|
|
|
self.expert_intermediate_size = expert_intermediate_size
|
|
|
self.shared_expert_intermediate_size = shared_expert_intermediate_size
|
|
|
self.router_aux_loss_coef = router_aux_loss_coef
|
|
|
self.use_checkpointing = use_checkpointing
|
|
|
self.rope_theta = rope_theta
|
|
|
super().__init__(**kwargs)
|
|
|
|
|
|
|
|
|
__all__ = ["EveConfig"]
|
|
|
|
