# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m Qwen/Qwen2.5-1.5B-Instruct -b auto -l 1319 -f 5 -t 1
model_name: "Qwen/Qwen2.5-1.5B-Instruct"
tasks:
- name: "gsm8k"
  metrics:
  - name: "exact_match,strict-match"
    value: 0.54
  - name: "exact_match,flexible-extract"
    value: 0.59
limit: 1319
num_fewshot: 5