dataset_path: WildVision/wildvision-arena-data
dataset_kwargs:
  token: True
output_type: generate_until
doc_to_visual: !function utils.wild_vision_doc_to_visual
doc_to_text: !function utils.wild_vision_doc_to_text
doc_to_target: !function utils.wild_vision_doc_to_target
process_results_use_image: true
generation_kwargs:
  max_new_tokens: 4096
  temperature: 0
  top_p: 1.0
  num_beams: 1
  do_sample: false
# The return value of process_results will be used by metrics
process_results: !function utils.wild_vision_process_results
# 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: gpt_eval_score
    aggregation: !function utils.wild_vision_aggregation
    higher_is_better: true
metadata:
  judge_model: gpt-4o
  baseline_model: claude-3-sonnet-20240229
