c90a6d3658
### What this PR does / why we need it?
Update the format of the accuracy report
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.10.2
- vLLM main:
c60e6137f0
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
16 lines
319 B
YAML
16 lines
319 B
YAML
model_name: "Qwen/Qwen3-8B-Base"
|
|
runner: "linux-aarch64-a2-1"
|
|
hardware: "Atlas A2 Series"
|
|
tasks:
|
|
- name: "gsm8k"
|
|
metrics:
|
|
- name: "exact_match,strict-match"
|
|
value: 0.82
|
|
- name: "exact_match,flexible-extract"
|
|
value: 0.83
|
|
- name: "ceval-valid"
|
|
metrics:
|
|
- name: "acc,none"
|
|
value: 0.82
|
|
num_fewshot: 5
|