13 lines
441 B
YAML
13 lines
441 B
YAML
# For vllm script, with -t option (tensor parallel size).
|
|
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise -b "auto" -l 1000 -f 5 -t 1
|
|
model_name: "nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise"
|
|
tasks:
|
|
- name: "gsm8k"
|
|
metrics:
|
|
- name: "exact_match,strict-match"
|
|
value: 0.595
|
|
- name: "exact_match,flexible-extract"
|
|
value: 0.582
|
|
limit: 1000
|
|
num_fewshot: 5
|