model_name: "Qwen/Qwen3-8B-Base" runner: "linux-aarch64-a2-1" hardware: "Atlas A2 Series" tasks: - name: "gsm8k" metrics: - name: "exact_match,strict-match" value: 0.82 - name: "exact_match,flexible-extract" value: 0.83 - name: "ceval-valid" metrics: - name: "acc,none" value: 0.82 num_fewshot: 5