# For vllm script, with -t option (tensor parallel size).
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen2-1.5B-Instruct-FP8W8 -b auto -l 1000 -f 5 -t 1
model_name: "nm-testing/Qwen2-1.5B-Instruct-FP8W8"
tasks:
- name: "gsm8k"
  metrics:
  - name: "exact_match,strict-match"
    value: 0.578
  - name: "exact_match,flexible-extract"
    value: 0.585
limit: 1000
num_fewshot: 5