mirror of
https://github.com/vllm-project/vllm.git
synced 2025-10-20 14:53:52 +08:00
13 lines
466 B
YAML
13 lines
466 B
YAML
# For hf script, without -t option (tensor parallel size).
|
|
# bash .buildkite/lm-eval-harness/run-lm-eval-chartqa-vllm-vlm-baseline.sh -m meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 -l 100 -t 8
|
|
model_name: "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
|
|
backend: "vllm-vlm"
|
|
tasks:
|
|
- name: "chartqa"
|
|
metrics:
|
|
- name: "relaxed_accuracy,none"
|
|
# TODO(zhewenl): model card is 0.90, but the actual score is 0.80.
|
|
value: 0.80
|
|
limit: 100
|
|
num_fewshot: 0
|