name: "docvqa"
task: "QA"
dataloader_model_task_as:
base_dataset_name: "ex_docvqa"
documents_count: 50 # 10.194 Documents in DocVQA train, 39,461 QA pairs
valid_labels: 
label_mapping: 
valid_secondary_labels:

prompt_template: "ClaudeRefined12"
prompt_task: "json"
prompt_params:
  num_solutions: 3
  doc_type: "business and administrative"
  language: "English"
  gt_type: "Multiple questions about each document, with their answers taken **verbatim** from the document."
  gt_format: '{"<Text of question 1>": "<Answer to question 1>", "<Text of question 2>": "<Answer to question 2>", ...}'

seed_selection_strategy: "v2"
seed_images_count: 6
hdbscan_min_cluster_size: 10
embedding_type: combined
alpha: 1
max_seed_pool: -1