b6afec73e1
### What this PR does / why we need it? Add accuracy nightly test for new models： PaddlePaddle/ERNIE-4.5-21B-A3B-PT LLM-Research/Molmo-7B-D-0924 LLM-Research/gemma-2-9b-it LLM-Research/gemma-3-4b-it Shanghai_AI_Laboratory/internlm-7b llava-hf/llava-1.5-7b-hf - vLLM version: v0.11.2 Signed-off-by: hfadzxy <starmoon_zhang@163.com>
14 lines
311 B
YAML
14 lines
311 B
YAML
model_name: "LLM-Research/gemma-3-4b-it"
|
|
hardware: "Atlas A2 Series"
|
|
tasks:
|
|
- name: "gsm8k"
|
|
metrics:
|
|
- name: "exact_match,strict-match"
|
|
value: 0.59
|
|
- name: "exact_match,flexible-extract"
|
|
value: 0.59
|
|
num_fewshot: 5
|
|
apply_chat_template: False
|
|
fewshot_as_multiturn: False
|
|
gpu_memory_utilization: 0.7
|