bge-m3-hf / configuration_bge_m3.py
liuyanyi's picture
Upload folder using huggingface_hub
8f08a66 verified
from transformers.configuration_utils import PretrainedConfig
# Copied from transformers.models.xlm_roberta.configuration_xlm_roberta.XLMRobertaConfig with XLMRoberta->BgeM3
class BgeM3Config(PretrainedConfig):
model_type = "bge-m3"
def __init__(
self,
vocab_size=30522,
hidden_size=768,
num_hidden_layers=12,
num_attention_heads=12,
intermediate_size=3072,
hidden_act="gelu",
hidden_dropout_prob=0.1,
attention_probs_dropout_prob=0.1,
max_position_embeddings=512,
type_vocab_size=2,
initializer_range=0.02,
layer_norm_eps=1e-12,
pad_token_id=1,
bos_token_id=0,
eos_token_id=2,
position_embedding_type="absolute",
use_cache=True,
classifier_dropout=None,
colbert_dim=None,
sentence_pooling_method='cls',
unused_tokens=None,
**kwargs,
):
super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
self.vocab_size = vocab_size
self.hidden_size = hidden_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.hidden_act = hidden_act
self.intermediate_size = intermediate_size
self.hidden_dropout_prob = hidden_dropout_prob
self.attention_probs_dropout_prob = attention_probs_dropout_prob
self.max_position_embeddings = max_position_embeddings
self.type_vocab_size = type_vocab_size
self.initializer_range = initializer_range
self.layer_norm_eps = layer_norm_eps
self.position_embedding_type = position_embedding_type
self.use_cache = use_cache
self.classifier_dropout = classifier_dropout
self.colbert_dim = colbert_dim
self.sentence_pooling_method = sentence_pooling_method
self.unused_tokens = unused_tokens