| 1 | # bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m RedHatAI/Llama-3.2-1B-Instruct-FP8 -b "auto" -l 1319 -f 5 -t 1 |
| 2 | model_name: "RedHatAI/Llama-3.2-1B-Instruct-FP8" |
| 3 | tasks: |
| 4 | - name: "gsm8k" |
| 5 | metrics: |
| 6 | - name: "exact_match,strict-match" |
| 7 | value: 0.335 |
| 8 | - name: "exact_match,flexible-extract" |
| 9 | value: 0.323 |
| 10 | limit: 1319 |
| 11 | num_fewshot: 5 |