feat: Migrate OSWorld files to HuggingFace cache with comprehensive documentation

- Add detailed README for file cache repository
- Implement migration script with retry logic and browser simulation
- Support automatic file type detection and deduplication
- Ensure reliable hosting for OSWorld evaluation files
This commit is contained in:
Timothyxxx
2025-05-28 04:29:37 +08:00
parent a845824f06
commit 34748567a5
317 changed files with 12630 additions and 12008 deletions

View File

@@ -10,11 +10,11 @@
"files": [
{
"path": "/home/user/Desktop/Employee Performance Evaluation Summary.xlsx",
"url": "https://drive.google.com/uc?id=1uOzi66bzO_WUnoS4Oqsodrd7_YPLatEk&export=download"
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/185f29bd-5da0-40a6-b69c-ba7f4e0324ef/Employee Performance Evaluation Summary.xlsx"
},
{
"path": "/home/user/Desktop/review_template.pdf",
"url": "https://drive.google.com/uc?id=1YJ4RPGFUuS48tBh31gBerA16JSMw498w&export=download"
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/185f29bd-5da0-40a6-b69c-ba7f4e0324ef/IC-Simple-Performance-Review-Template-10796_PDF.pdf"
}
]
}
@@ -49,13 +49,13 @@
"result": {
"type": "cloud_file",
"path": [
"https://drive.google.com/uc?id=1kZM90nA1krRmV9ug5_BBe8VlrZRVLiLK&export=download",
"https://drive.google.com/uc?id=1zyLzYYThwyit9ciXpfNfPFlBomolOauY&export=download",
"https://drive.google.com/uc?id=1gMT7JBftuymajMAO5rwksORpeVq3uGmH&export=download",
"https://drive.google.com/uc?id=1x0DdtUSZyBifl1tGIWlWKn255WusJeR4&export=download",
"https://drive.google.com/uc?id=1UAcG32WO8XCXElcanjGwbSpJwFuyOkts&export=download",
"https://drive.google.com/uc?id=1PRgryg7Y5evKnDG2LPtAttVp9qAf5VyZ&export=download",
"https://drive.google.com/uc?id=1JxEDriCS2W7BQLdkIgxu_WFCRa9ib4D7&export=download"
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/185f29bd-5da0-40a6-b69c-ba7f4e0324ef/Alex Lee.pdf",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/185f29bd-5da0-40a6-b69c-ba7f4e0324ef/David Wilson.pdf",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/185f29bd-5da0-40a6-b69c-ba7f4e0324ef/Emily Johnson.pdf",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/185f29bd-5da0-40a6-b69c-ba7f4e0324ef/John Doe.pdf",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/185f29bd-5da0-40a6-b69c-ba7f4e0324ef/Linda Green.pdf",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/185f29bd-5da0-40a6-b69c-ba7f4e0324ef/Michael Brown.pdf",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/185f29bd-5da0-40a6-b69c-ba7f4e0324ef/Sophia Carter.pdf"
],
"dest": [
"Alex Lee_Gold.pdf",
@@ -67,7 +67,15 @@
"Sophia Carter_Gold.pdf"
],
"multi": true,
"gives": [0,1,2,3,4,5,6]
"gives": [
0,
1,
2,
3,
4,
5,
6
]
},
"expected": {
"type": "vm_file",
@@ -90,7 +98,15 @@
"Sophia Carter.pdf"
],
"multi": true,
"gives": [0,1,2,3,4,5,6]
"gives": [
0,
1,
2,
3,
4,
5,
6
]
}
}
}
}