| 1 | # For vllm script, with -t option (tensor parallel size). |
| 2 | # bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test -b auto -l 1000 -f 5 -t 1 |
| 3 | model_name: "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test" |
| 4 | tasks: |
| 5 | - name: "gsm8k" |
| 6 | metrics: |
| 7 | - name: "exact_match,strict-match" |
| 8 | value: 0.758 |
| 9 | - name: "exact_match,flexible-extract" |
| 10 | value: 0.759 |
| 11 | limit: 1000 |
| 12 | num_fewshot: 5 |