diff --git a/.github/workflows/accuracy_test.yaml b/.github/workflows/accuracy_test.yaml index a7d3c786b8..99b521aae0 100644 --- a/.github/workflows/accuracy_test.yaml +++ b/.github/workflows/accuracy_test.yaml @@ -59,6 +59,8 @@ jobs: model_name: DeepSeek-V2-Lite - runner: a2-4 model_name: Qwen3-Next-80B-A3B-Instruct + - runner: a2-1 + model_name: Mistral-7B-Instruct-v0.1 fail-fast: false # test will be triggered when tag 'accuracy-test' & 'ready-for-test' if: >- diff --git a/tests/e2e/models/configs/Mistral-7B-Instruct-v0.1.yaml b/tests/e2e/models/configs/Mistral-7B-Instruct-v0.1.yaml new file mode 100644 index 0000000000..bf3c1618db --- /dev/null +++ b/tests/e2e/models/configs/Mistral-7B-Instruct-v0.1.yaml @@ -0,0 +1,11 @@ +model_name: "mistralai/Mistral-7B-Instruct-v0.1" +hardware: "Atlas A2 Series" +tasks: +- name: "gsm8k" + metrics: + - name: "exact_match,strict-match" + value: 0.35 + - name: "exact_match,flexible-extract" + value: 0.38 +trust_remote_code: True +num_fewshot: 5