# For vllm script, with -t option (tensor parallel size).
# bash .buildkite/lm-eval-harness/run-lm-eval-chartqa-vllm-vlm-baseline.sh -m Qwen/Qwen2.5-VL-7B-Instruct -l 2500 -t 1

model_name: "Qwen/Qwen2.5-VL-7B-Instruct"
backend: "vllm-vlm"
tasks:
- name: "chartqa"
  metrics:
  - name: "relaxed_accuracy,none"
    value: 0.855
limit: 2500
num_fewshot: 0