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

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=13aX_EkeTbuyFVeIkwVU_YB2f7ZbvRqR8&export=download&authuser=0&confirm=t&uuid=1be9020d-d0ab-4426-8fb9-e337d7bbaac1&at=APZUnTW6wfDLvzjHRfsh9cikK35W:1710926958131",
"url": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/3b27600c-3668-4abd-8f84-7bcdebbccbdb/lec17-gui-events.pptx",
"path": "C:\\Users\\User\\lec17-gui-events.pptx"
}
]

View File

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1jrzNIGxiasIXHSc0rNlrdKr4nASGiolw&export=download&authuser=0&confirm=t&uuid=a00d2846-65fb-4db0-9763-c750e0c336c6&at=APZUnTXpm9eCM4cFu09MkeVQns7b:1710936041868",
"url": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/455d3c66-7dc6-4537-a39a-36d3e9119df7/wssf-project-plan-on-a-page.pptx",
"path": "C:\\Users\\User\\wssf-project-plan-on-a-page.pptx"
}
]
@@ -61,7 +61,7 @@
"func": "compare_images",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1C5-lKdzpC3Y8dvdXj84fymPtlqLN0FR-&export=download&authuser=0&confirm=t&uuid=a12f0635-839e-4196-bbae-7ec754f95c94&at=APZUnTVsrVGYT7WvkhkMUej5v9fz:1710942950188",
"path": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/455d3c66-7dc6-4537-a39a-36d3e9119df7/res.png",
"dest": "res_gold.png"
},
"result": {

View File

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1uPIsYoecxaADGDuWA-EbzH77oTiYaPx_&export=download&authuser=0&confirm=t&uuid=5925548f-2d57-457d-b107-2ecea35668bf&at=APZUnTUc1rS7g-u5EbBsiWl9hj03:1711004778606",
"url": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/550ce7e7-747b-495f-b122-acdc4d0b8e54/New_Club_Spring_2018_Training.pptx",
"path": "C:\\Users\\User\\New_Club_Spring_2018_Training.pptx"
}
]
@@ -77,7 +77,7 @@
"func": "compare_pptx_files",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1-0-7a8E0-Rye6QbuOaj0UwIqcc3gEM6J&export=download&authuser=0&confirm=t&uuid=64e43c6e-ee8a-45fb-aaf2-8636a8ae422b&at=APZUnTXRYH6X5sEXW_kbuN204uWt:1711004798314",
"path": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/550ce7e7-747b-495f-b122-acdc4d0b8e54/New_Club_Spring_2018_Training_Gold.pptx",
"dest": "New_Club_Spring_2018_Training_Gold.pptx"
},
"result": {

View File

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1Y-MapQ2WrJoz0xcpLe3VZeK9VdN6hQ_1&export=download&authuser=0&confirm=t&uuid=dd374dbf-aa2d-4794-ab6a-822b0e759050&at=APZUnTX2Qh2kU65JKWhD0BsVtowm:1710927428289",
"url": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/5d901039-a89c-4bfb-967b-bf66f4df075e/CPD_Background_Investigation_Process.pptx",
"path": "C:\\Users\\User\\CPD_Background_Investigation_Process.pptx"
}
]
@@ -61,7 +61,7 @@
"func": "check_image_stretch_and_center",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1Y-MapQ2WrJoz0xcpLe3VZeK9VdN6hQ_1&export=download&authuser=0&confirm=t&uuid=dd374dbf-aa2d-4794-ab6a-822b0e759050&at=APZUnTX2Qh2kU65JKWhD0BsVtowm:1710927428289",
"path": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/5d901039-a89c-4bfb-967b-bf66f4df075e/CPD_Background_Investigation_Process.pptx",
"dest": "CPD_Background_Investigation_Process_Original.pptx"
},
"result": {

View File

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=14mkSm2Dv0jA-qyLm65knVegEABUiM41o&export=download&authuser=0&confirm=t&uuid=2d461911-0ced-465d-a721-7f0bcca49a92&at=APZUnTXaHJSNDXL2dGZa4jvaTmgj:1710940747817",
"url": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/9ec204e4-f0a3-42f8-8458-b772a6797cab/MLA_Workshop_061X_Works_Cited.pptx",
"path": "C:\\Users\\User\\MLA_Workshop_061X_Works_Cited.pptx"
}
]
@@ -61,7 +61,7 @@
"func": "compare_pptx_files",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=16v7zubD_Hu8XFPtp8SiH60Azg5hvJCs4&export=download&authuser=0&confirm=t&uuid=94547bc1-2764-46bc-974f-1b31abebaa2d&at=APZUnTVTpKFXWpv2kHg_KW2mXT5U:1710940711249",
"path": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/9ec204e4-f0a3-42f8-8458-b772a6797cab/MLA_Workshop_061X_Works_Cited_Gold.pptx",
"dest": "MLA_Workshop_061X_Works_Cited_Gold.pptx"
},
"result": {

View File

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1c2QgyKsNpBvjw2zLGyk4lxM9L-Mr_986&export=download&authuser=0&confirm=t&uuid=31e05bc4-37c8-45c6-8ae9-15ede6202f54&at=APZUnTVMRuXMqUARayy64cvAgKUN:1710944701562",
"url": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/a097acff-6266-4291-9fbd-137af7ecd439/Secrets-of-Monetizing-Video.pptx",
"path": "C:\\Users\\User\\Downloads\\Secrets-of-Monetizing-Video.pptx"
}
]
@@ -30,7 +30,7 @@
"func": "compare_pptx_files",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1c2QgyKsNpBvjw2zLGyk4lxM9L-Mr_986&export=download&authuser=0&confirm=t&uuid=31e05bc4-37c8-45c6-8ae9-15ede6202f54&at=APZUnTVMRuXMqUARayy64cvAgKUN:1710944701562",
"path": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/a097acff-6266-4291-9fbd-137af7ecd439/Secrets-of-Monetizing-Video.pptx",
"dest": "Secrets-of-Monetizing-Video.pptx"
},
"result": {

View File

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1Vpv15scw1zbRAzFx_1nkgG9ROKzCV_1R&export=download&authuser=0&confirm=t&uuid=fb81a042-cc55-4b8c-89c0-51e30c872749&at=APZUnTWufEjoMu2mj1AKkcgkfc4J:1710945229686",
"url": "https://huggingface.co/datasets/xlangai/windows_osworld_file_cache/resolve/main/ppt/ce88f674-ab7a-43da-9201-468d38539e4a/AM_Last_Page_Template.pptx",
"path": "C:\\Users\\User\\AM_Last_Page_Template.pptx"
}
]