| 1 | # For vllm script, with -t option (tensor parallel size). |
| 2 | # bash .buildkite/lm-eval-harness/run-lm-eval-chartqa-vllm-vlm-baseline.sh -m Qwen/Qwen2.5-VL-7B-Instruct -l 2500 -t 1 |
| 3 | |
| 4 | model_name: "Qwen/Qwen2.5-VL-7B-Instruct" |
| 5 | backend: "vllm-vlm" |
| 6 | tasks: |
| 7 | - name: "chartqa" |
| 8 | metrics: |
| 9 | - name: "relaxed_accuracy,none" |
| 10 | value: 0.855 |
| 11 | limit: 2500 |
| 12 | num_fewshot: 0 |