Files
xc-llm-ascend/tests/e2e/singlecard/pooling/template/qwen3_reranker.jinja
yupeng 29f195a91c [Bugfix][LoRA] Fix the bug when runs Qwen3-Reranker-0.6B with LoRA. (#7156)
### What this PR does / why we need it?
Fix the error that reports while initializing qwen3-reranker-0.6b model
with `--enable-lora`.
And add a testcase to verify the fix.

- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: paulyu12 <507435917@qq.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
2026-03-15 17:55:42 +08:00

12 lines
624 B
Django/Jinja
Executable File

<|im_start|>system
Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>
<|im_start|>user
<Instruct>: {{ messages | selectattr("role", "eq", "system") | map(attribute="content") | first | default("Given a web search query, retrieve relevant passages that answer the query") }}
<Query>: {{ messages | selectattr("role", "eq", "query") | map(attribute="content") | first }}
<Document>: {{ messages | selectattr("role", "eq", "document") | map(attribute="content") | first }}<|im_end|>
<|im_start|>assistant
<think>
</think>