Harness/run 1110

[zhentaocc]

        model_name: [Llama2-7b-guanaco-dolphin-500, Llama-2-7b-chat-hf]
        task: ["truthfulqa", "arc", "mmlu", "hellaswag"]
        precision: ["mixed_fp8"] #options: sym_int4, fp4, nf4, mixed_4bit, fp8
        include:
          - python-version: 3.9
            model_name: Llama2-7b-guanaco-dolphin-500
            task: truthfulqa
            precision: sym_int4 #options: sym_int4, fp4, nf4, mixed_4bit, fp8
          - python-version: 3.9
            model_name: Llama-2-7b-chat-hf
            task: mmlu
            precision: sym_int4 #options: sym_int4, fp4, nf4, mixed_4bit, fp8

[liu-shaojun]

@zhentaocc Did you add a submodule by mistake? That caused other tests to fail because source code cached, could you delete the submodule?

[zhentaocc]

@zhentaocc Did you add a submodule by mistake? That caused other tests to fail because source code cached, could you delete the submodule?

done