lmms_eval/tasks/seedbench/seedbench_ppl.yaml

dataset_path: lmms-lab/SEED-Bench
dataset_kwargs:
  token: True
task: "seedbench_ppl"
test_split: test
output_type: multiple_choice
doc_to_visual: !function utils.seed_doc_to_visual
doc_to_text: !function utils.seed_doc_to_text_mc
doc_to_choice : !function utils.seed_doc_to_choice
doc_to_target: !function utils.seed_doc_to_mc_target
# Note that the metric name can be either a registed metric function (such as the case for GQA) or a key name returned by process_results
metric_list:
  - metric: acc
metadata:
  - version: 0.0