biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model] Enable optional prefix when loading embedding models (#10639)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-11-26 02:14:33 +08:00
committed by GitHub
parent b1d920531f
commit cf73f0c95e
5 changed files with 20 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/models/roberta.py
View File

@@ -11,13 +11,14 @@ from vllm.model_executor.layers.vocab_parallel_embedding import (
VocabParallelEmbedding)
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.models.bert import BertEmbeddingModel, BertModel
from vllm.model_executor.models.interfaces import SupportsCrossEncoding
from vllm.model_executor.models.utils import maybe_prefix
from vllm.model_executor.pooling_metadata import PoolingMetadata
from vllm.sequence import IntermediateTensors, PoolerOutput
from vllm.transformers_utils.config import (
get_cross_encoder_activation_function)
from .interfaces import SupportsCrossEncoding
class RobertaEmbedding(nn.Module):