Qwen2-57B-A14-Instruct.yaml

# For vllm script, with -t option (tensor parallel size).
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m Qwen/Qwen2-57B-A14B-Instruct -b "auto" -l 250 -f 5 -t 4
model_name: "Qwen/Qwen2-57B-A14B-Instruct"
tasks:
- name: "gsm8k"
  metrics:
  - name: "exact_match,strict-match"
    value: 0.792
  - name: "exact_match,flexible-extract"
    value: 0.824
limit: 250
num_fewshot: 5