mirror of
https://github.com/microsoft/SkillOpt.git
synced 2026-07-05 15:27:51 +08:00
37 lines
1.0 KiB
JSON
37 lines
1.0 KiB
JSON
{
|
|
"benchmark": "DocVQA",
|
|
"manifest_type": "id_split",
|
|
"source_repo": "lmms-lab/DocVQA",
|
|
"source_repo_type": "dataset",
|
|
"source_url": "https://huggingface.co/datasets/lmms-lab/DocVQA",
|
|
"source_revision": "539088ef8a8ada01ac8e2e6d4e372586748a265e",
|
|
"source_config": "DocVQA",
|
|
"source_split": "validation",
|
|
"source_split_name": "docvqa_validation_10pct",
|
|
"split_method": "10% subset sampled from the DocVQA validation split",
|
|
"counts": {
|
|
"train": 107,
|
|
"val": 53,
|
|
"test": 374
|
|
},
|
|
"item_fields": [
|
|
"id",
|
|
"questionId",
|
|
"docId",
|
|
"image_path",
|
|
"ucsf_document_id",
|
|
"ucsf_document_page_no",
|
|
"topic",
|
|
"source_dataset",
|
|
"source_config",
|
|
"source_split",
|
|
"sample_seed"
|
|
],
|
|
"notes": [
|
|
"This is a split manifest, not the full DocVQA payload.",
|
|
"Materialize full CSV rows and image files before evaluation.",
|
|
"This manifest corresponds to docvqa_validation_10pct.",
|
|
"All released train/val/test items originate from a 10% subset of the official DocVQA validation split."
|
|
]
|
|
}
|