Files
xc-llm-ascend/tests/e2e/models/configs/Qwen2-Audio-7B-Instruct.yaml
zhangxinyuehfad d913f9474b [0.11.0][Fix] Fix Qwen2-Audio-7B-Instruct accuracy test (#4018)
### What this PR does / why we need it?

Fix Qwen2-Audio-7B-Instruct accuracy test

Backport:https://github.com/vllm-project/vllm-ascend/pull/4017

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
2025-11-10 11:54:30 +08:00

12 lines
258 B
YAML

model_name: "Qwen/Qwen2-Audio-7B-Instruct"
hardware: "Atlas A2 Series"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.44
- name: "exact_match,flexible-extract"
value: 0.45
num_fewshot: 5
gpu_memory_utilization: 0.8