f3c378ffa7
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com> Signed-off-by: zhewenli <zhewenli@meta.com> Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com> Co-authored-by: Ye (Charlotte) Qi <ye.charlotte.qi@gmail.com>
13 lines
413 B
YAML
13 lines
413 B
YAML
# For vllm script, with -t option (tensor parallel size)
|
|
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic -l 1319 -t 1
|
|
model_name: "RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic"
|
|
tasks:
|
|
- name: "gsm8k"
|
|
metrics:
|
|
- name: "exact_match,strict-match"
|
|
value: 0.47
|
|
- name: "exact_match,flexible-extract"
|
|
value: 0.64
|
|
limit: 1319
|
|
num_fewshot: 5
|