# For vllm script, with -t option (tensor parallel size).
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16 -b auto -l 1319 -f 5 -t 1
model_name: "nm-testing/Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16"
tasks:
- name: "gsm8k"
  metrics:
  - name: "exact_match,strict-match"
    value: 0.30
  - name: "exact_match,flexible-extract"
    value: 0.465
limit: 1319
num_fewshot: 5