# For vllm script, with -t option (tensor parallel size).
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Mixtral-8x22B-Instruct-v0.1-FP8-dynamic -b "auto" -l 250 -f 5 -t 8
model_name: "neuralmagic/Mixtral-8x22B-Instruct-v0.1-FP8-dynamic"
tasks:
- name: "gsm8k"
  metrics:
  - name: "exact_match,strict-match"
    value: 0.86
  - name: "exact_match,flexible-extract"
    value: 0.86
limit: 250
num_fewshot: 5