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

[Model] Automatic conversion of TokenClassification model (#30666)

Browse Source 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2025-12-15 16:13:00 +08:00
committed by GitHub
parent 33278073d6
commit 4429d934de
4 changed files with 45 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/config/model.py
View File

@@ -1796,6 +1796,7 @@ _SUFFIX_TO_DEFAULTS: list[tuple[str, tuple[RunnerType, ConvertType]]] = [
("ForTextEncoding", ("pooling", "embed")),
("EmbeddingModel", ("pooling", "embed")),
("ForSequenceClassification", ("pooling", "classify")),
("ForTokenClassification", ("pooling", "classify")),
("ForAudioClassification", ("pooling", "classify")),
("ForImageClassification", ("pooling", "classify")),
("ForVideoClassification", ("pooling", "classify")),