configs/gpu.yaml

gpu:
  backend: transformers
  provider: huggingface_spaces
  space_name: zeroshotGPU
  batch_pages: true
  validate_tasks: true
  max_batch_size: 4
  max_gpu_seconds_per_doc: 120
  max_vlm_calls_per_doc: 30
  models:
    vlm:
      model_id: Qwen/Qwen2.5-VL-3B-Instruct
      task: image-text-to-text
      device: auto
      dtype: bfloat16
      max_batch_size: 1
    ocr:
      model_id: Qwen/Qwen2.5-VL-3B-Instruct
      task: document-ocr
      device: auto
      dtype: bfloat16
      max_batch_size: 1
    table:
      model_id: Qwen/Qwen2.5-VL-3B-Instruct
      task: table-repair
      device: auto
      dtype: bfloat16
      max_batch_size: 1
    embedding:
      model_id: jinaai/jina-embeddings-v3
      task: retrieval.passage
      device: auto
      dtype: bfloat16
      max_batch_size: 16
  task_model_roles:
    vlm_route_repair: vlm
    ocr_page: ocr
    table_vlm_repair: table
    figure_description: vlm

deployment:
  target: huggingface_spaces
  gpu_models_target: zeroshotGPU