f3c378ffa7
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com> Signed-off-by: zhewenli <zhewenli@meta.com> Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com> Co-authored-by: Ye (Charlotte) Qi <ye.charlotte.qi@gmail.com>
12 lines
451 B
YAML
12 lines
451 B
YAML
# For hf script, without -t option (tensor parallel size).
|
|
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 -b 32 -l 250 -t 8 -f 5
|
|
model_name: "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
|
|
backend: "vllm-vlm"
|
|
tasks:
|
|
- name: "mmlu_pro"
|
|
metrics:
|
|
- name: "exact_match,custom-extract"
|
|
value: 0.80
|
|
limit: 250 # will run on 250 * 14 subjects = 3500 samples
|
|
num_fewshot: 5
|