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

@@ -7,46 +7,97 @@
{
"type": "execute",
"parameters": {
"command": ["mkdir", "-p", "/home/user/Documents/Finance/receipts", "/home/user/Documents/Projects/OSWorld", "/home/user/Documents/Novels/4th Year in Tsinghua"]
"command": [
"mkdir",
"-p",
"/home/user/Documents/Finance/receipts",
"/home/user/Documents/Projects/OSWorld",
"/home/user/Documents/Novels/4th Year in Tsinghua"
]
}
},
{
"type": "download",
"parameters": {
"files": [
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2308.pdf", "url": "https://drive.google.com/uc?id=1azRFXf4A7fvW0S7r9upHvleMEi-92hHM&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2309.pdf", "url": "https://drive.google.com/uc?id=1x-lpHm8U4U7uRPZ74-9wq9KzW2R55ln1&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2310.pdf", "url": "https://drive.google.com/uc?id=1pcrgV9G6NO4ekMEQBiupwXtq6mmke7b_&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2311.pdf", "url": "https://drive.google.com/uc?id=1JzbCK_nIY8X_3QZjnkzTtb-cRoq9zNT-&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2312.pdf", "url": "https://drive.google.com/uc?id=1RqbulzKG_HeYb1GZmLABOzlohlFg02UU&export=download"},
{"path": "/home/user/Documents/Finance/receipts/X-receipt-2312.pdf", "url": "https://drive.google.com/uc?id=1QzWjNzvNosG_yQr7VVonvYb3cUYF5f3u&export=download"},
{"path": "/home/user/Documents/Finance/tally_book.xlsx", "url": "https://drive.google.com/uc?id=13yuLhBPmouoWR-DybfgaIbWUOxbY_jhL&export=download"},
{"path": "/home/user/.projects.tar.xz", "url": "https://drive.google.com/uc?id=1oJcxpjqF474Wm16i1aZc8DlCEfAvc4t_&export=download"},
{"path": "/home/user/.old-chapters.tar.xz", "url": "https://drive.google.com/uc?id=11y-kLI83sQz6ncmP1-tkIR6mQJ7SfX5-&export=download"}
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2308.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/788b3701-3ec9-4b67-b679-418bfa726c22/invoice0123456789-2308.pdf"
},
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2309.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/788b3701-3ec9-4b67-b679-418bfa726c22/invoice0123456789-2309.pdf"
},
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2310.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/788b3701-3ec9-4b67-b679-418bfa726c22/invoice0123456789-2310.pdf"
},
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2311.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/788b3701-3ec9-4b67-b679-418bfa726c22/invoice0123456789-2311.pdf"
},
{
"path": "/home/user/Documents/Finance/receipts/aws-invoice-2312.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/788b3701-3ec9-4b67-b679-418bfa726c22/invoice0123456789-2312.pdf"
},
{
"path": "/home/user/Documents/Finance/receipts/X-receipt-2312.pdf",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/788b3701-3ec9-4b67-b679-418bfa726c22/Receipt-0123-4567.pdf"
},
{
"path": "/home/user/Documents/Finance/tally_book.xlsx",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/788b3701-3ec9-4b67-b679-418bfa726c22/tally_book.xlsx"
},
{
"path": "/home/user/.projects.tar.xz",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/788b3701-3ec9-4b67-b679-418bfa726c22/projects.tar.xz"
},
{
"path": "/home/user/.old-chapters.tar.xz",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/788b3701-3ec9-4b67-b679-418bfa726c22/old-chapters.tar.xz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": ["tar", "-xJvf", "/home/user/.projects.tar.xz", "-C", "/home/user/Documents/Projects/OSWorld"]
"command": [
"tar",
"-xJvf",
"/home/user/.projects.tar.xz",
"-C",
"/home/user/Documents/Projects/OSWorld"
]
}
},
{
"type": "execute",
"parameters": {
"command": ["tar", "-xJvf", "/home/user/.old-chapters.tar.xz", "-C", "/home/user/Documents/Novels/4th Year in Tsinghua"]
"command": [
"tar",
"-xJvf",
"/home/user/.old-chapters.tar.xz",
"-C",
"/home/user/Documents/Novels/4th Year in Tsinghua"
]
}
},
{
"type": "launch",
"parameters": {
"command": ["nautilus", "/home/user/Documents/Novels/4th Year in Tsinghua"]
"command": [
"nautilus",
"/home/user/Documents/Novels/4th Year in Tsinghua"
]
}
}
],
"trajectory": "trajectories/788b3701-3ec9-4b67-b679-418bfa726c22",
"related_apps": ["chrome", "os"],
"related_apps": [
"chrome",
"os"
],
"evaluator": {
"func": "diff_text_file",
"result": {
@@ -56,8 +107,8 @@
},
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1kiCDbTn7uYfgqbymddC5IKMsvpkihW-s&export=download",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/788b3701-3ec9-4b67-b679-418bfa726c22/早期建筑群.tex",
"dest": "real.tex"
}
}
}
}