Llamoe-test / configuration_Llamoe.py
damerajee's picture
Update configuration_Llamoe.py
e34c61b verified
raw
history blame
2.29 kB
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
LLAMOE_PRETRAINED_CONFIG_ARCHIVE_MAP = {
"damerajee/Llamoe-test": "https://huggingface.co/damerajee/Llamoe-test/resolve/main/config.json",
}
class LlamoeConfig(PretrainedConfig):
model_type = "Llamoe"
keys_to_ignore_at_inference = ["past_key_values"]
def __init__(
self,
vocab_size=32000,
hidden_size=4096,
intermediate_size=11008,
num_hidden_layers=32,
num_attention_heads=32,
num_key_value_heads=32,
head_dim=128,
hidden_act="silu",
max_position_embeddings=2048,
initializer_range=0.02,
rms_norm_eps=1e-06,
use_cache=True,
pad_token_id=0,
eos_token_id=1,
bos_token_id=2,
tie_word_embeddings=False,
rope_theta=10000.0,
attention_bias=False,
attention_dropout=0.0,
num_experts_per_tok=2,
num_local_experts=8,
router_aux_loss_coef=0.02,
output_router_logits=False,
**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
self.head_dim = head_dim
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.rope_theta = rope_theta
self.attention_bias = attention_bias
self.attention_dropout = attention_dropout
self.num_experts_per_tok = num_experts_per_tok
self.num_local_experts = num_local_experts
self.router_aux_loss_coef = router_aux_loss_coef
self.output_router_logits = output_router_logits
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,
)