2025-04-27 02:25:05 +08:00
|
|
|
# For vllm script, with -t option (tensor parallel size).
|
2024-07-07 16:42:11 -04:00
|
|
|
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test -b "auto" -l 250 -f 5 -t 1
|
|
|
|
|
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test"
|
|
|
|
|
tasks:
|
|
|
|
|
- name: "gsm8k"
|
|
|
|
|
metrics:
|
|
|
|
|
- name: "exact_match,strict-match"
|
|
|
|
|
value: 0.728
|
|
|
|
|
- name: "exact_match,flexible-extract"
|
|
|
|
|
value: 0.728
|
|
|
|
|
limit: 250
|
|
|
|
|
num_fewshot: 5
|
