# For vllm script, with -t option (tensor parallel size).
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-chnl_wts_per_tok_dyn_act_fp8-BitM -b "auto" -t 2
model_name: "nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-chnl_wts_per_tok_dyn_act_fp8-BitM"
tasks:
- name: "gsm8k"
  metrics:
  - name: "exact_match,strict-match"
    value: 0.6353
  - name: "exact_match,flexible-extract"
    value: 0.637
limit: null
num_fewshot: null