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

[Model] Let more models to support the score template. (#31335)

Browse Source 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
wang.yuqi
2026-01-05 19:54:26 +08:00
committed by GitHub
parent caaa482aca
commit 911d38ed99
23 changed files with 764 additions and 334 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/config.py
View File

@@ -251,7 +251,7 @@ class Qwen3ForSequenceClassificationConfig(VerifyAndUpdateConfig):
tokens = getattr(config, "classifier_from_token", None)
assert tokens is not None and len(tokens) == 2, (
"Try loading the original Qwen3 Reranker?, see: "
"https://github.com/vllm-project/vllm/tree/main/examples/offline_inference/offline_reranker.py"
"https://github.com/vllm-project/vllm/tree/main/examples/pooling/score/qwen3_reranker_offline.py"
)
model_config.hf_config.method = "from_2_way_softmax"