|
|
|
|
|
|
|
|
from transformers import PretrainedConfig |
|
|
from transformers.modeling_rope_utils import rope_config_validation |
|
|
|
|
|
|
|
|
class KORMoMoeConfig(PretrainedConfig): |
|
|
model_type = "kormo_moe" |
|
|
keys_to_ignore_at_inference = ["past_key_values"] |
|
|
|
|
|
def __init__( |
|
|
self, |
|
|
vocab_size=112576, |
|
|
hidden_size=6144, |
|
|
intermediate_size=21504, |
|
|
num_hidden_layers=48, |
|
|
num_attention_heads=40, |
|
|
num_key_value_heads=8, |
|
|
hidden_act="silu", |
|
|
max_position_embeddings=131072, |
|
|
initializer_range=0.02, |
|
|
rms_norm_eps=1e-05, |
|
|
use_cache=True, |
|
|
pad_token_id=None, |
|
|
bos_token_id=0, |
|
|
eos_token_id=1, |
|
|
pretraining_tp=1, |
|
|
tie_word_embeddings=False, |
|
|
rope_theta=500000.0, |
|
|
attention_bias=False, |
|
|
attention_dropout=0.0, |
|
|
rope_scaling=None, |
|
|
mlp_bias=False, |
|
|
head_dim=128, |
|
|
|
|
|
num_experts=2, |
|
|
num_experts_per_tok=2, |
|
|
moe_intermediate_size=None, |
|
|
shared_expert_intermediate_size=None, |
|
|
norm_topk_prob=True, |
|
|
decoder_sparse_step=1, |
|
|
**kwargs, |
|
|
): |
|
|
self.vocab_size = vocab_size |
|
|
self.max_position_embeddings = max_position_embeddings |
|
|
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.pretraining_tp = pretraining_tp |
|
|
self.use_cache = use_cache |
|
|
self.rope_theta = rope_theta |
|
|
self.rope_scaling = rope_scaling |
|
|
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 |
|
|
self.mask_type = None |
|
|
|
|
|
|
|
|
self.num_experts = num_experts |
|
|
self.num_experts_per_tok = num_experts_per_tok |
|
|
self.moe_intermediate_size = moe_intermediate_size if moe_intermediate_size is not None else intermediate_size |
|
|
self.shared_expert_intermediate_size = shared_expert_intermediate_size |
|
|
self.norm_topk_prob = norm_topk_prob |
|
|
self.decoder_sparse_step = decoder_sparse_step |
|
|
|
|
|
if self.rope_scaling is not None and "type" in self.rope_scaling: |
|
|
self.rope_scaling["rope_type"] = self.rope_scaling["type"] |
|
|
rope_config_validation(self) |
|
|
|
|
|
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, |
|
|
) |
