lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Migrate OSWorld files to HuggingFace cache with comprehensive documentation

Browse Source 
- 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
Download Patch File Download Diff File Expand all files Collapse all files

17
evaluation_examples/examples/os/23393935-50c7-4a86-aeea-2b78fd089c5c.json
View File

@@ -31,7 +31,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1H7R6flpv6vgyBOHurzR0CyvPRIobuIpI&export=download&authuser=0&confirm=t&uuid=1b41e87d-7a84-4aa6-af40-cf940e80d956&at=APZUnTWus2n1pP6l2wmIyXkCUHGs:1706196492307",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/23393935-50c7-4a86-aeea-2b78fd089c5c/monk252520thailand252520wat252520arun252520scaled25255B225255D.jpg",
"path": "/home/user/Desktop/photos/vacation/thailand/monk252520thailand252520wat252520arun252520scaled25255B225255D.jpg"
}
]
@@ -42,7 +42,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1Mh3kIViHaayxNC88TpgpjbmIEl17LA3d&export=download&authuser=0&confirm=t&uuid=a8355b84-aa2e-4502-8d0f-3723ffe7d442&at=APZUnTW4nzDFgDgNeERMRKEQ4bTU:1706196493503",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/23393935-50c7-4a86-aeea-2b78fd089c5c/hong-kong-china.jpg",
"path": "/home/user/Desktop/photos/vacation/hk/hong-kong-china.jpg"
}
]
@@ -53,7 +53,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1EhmbZ3QP_mdvvppC5zKA3o--Ce2F-ocO&export=download&authuser=0&confirm=t&uuid=70e05133-dcac-4168-b555-82da15a10d58&at=APZUnTXJ371jG7qiPLHBLt2zy7ij:1706196494612",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/23393935-50c7-4a86-aeea-2b78fd089c5c/hk_group_photo.jpg",
"path": "/home/user/Desktop/photos/vacation/hk/hk_group_photo.jpg"
}
]
@@ -64,7 +64,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1p_r_BMCLFG872uH9Qa-sLnqXppHvDx95&export=download&authuser=0&confirm=t&uuid=af59d107-8e46-4d2c-b72a-e4b42655959a&at=APZUnTU2hBidSnefJuUQTyJCEVFx:1706196491030",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/23393935-50c7-4a86-aeea-2b78fd089c5c/us_3.png",
"path": "/home/user/Desktop/photos/family/us_3.png"
}
]
@@ -75,7 +75,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1YxryNHfLPcFODnUh31CYGHGj3ZFRhvbA&export=download&authuser=0&confirm=t&uuid=0925ae33-ab33-42b9-901c-d90f11e0afcd&at=APZUnTVey7VeC9zYOmTwl0x02Iwf:1706196495770",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/23393935-50c7-4a86-aeea-2b78fd089c5c/emnlp2023.jpg",
"path": "/home/user/Desktop/photos/events/emnlp2023.jpg"
}
]
@@ -104,7 +104,12 @@
"expected": {
"type": "rule",
"rules": {
"expected": ["emnlp2023.jpg", "hk_group_photo.jpg", "hong-kong-china.jpg", "monk252520thailand252520wat252520arun252520scaled25255B225255D.jpg"]
"expected": [
"emnlp2023.jpg",
"hk_group_photo.jpg",
"hong-kong-china.jpg",
"monk252520thailand252520wat252520arun252520scaled25255B225255D.jpg"
]
}
}
}

9
evaluation_examples/examples/os/37887e8c-da15-4192-923c-08fa390a176d.json
View File

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1auLclNUSBieSHZp2tLOUT7tA0ejzz4X6&export=download&authuser=0&confirm=t&uuid=142ef302-89af-4511-afa7-11ec7e8c3397&at=APZUnTVxFDmqv0dbWMC0VdlRziXD:1707992474338",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/37887e8c-da15-4192-923c-08fa390a176d/setup.sh",
"path": "setup.sh"
}
]
@@ -57,7 +57,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1DakvqJfSokEPuH8_LYfSCBbM7Fws1F0o&export=download&authuser=0&confirm=t&uuid=42428619-921a-4405-abbf-e5fa7ea0e1b7&at=APZUnTX6nAbw51hosLfUD5CftRg6:1708528738860",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/37887e8c-da15-4192-923c-08fa390a176d/eval.sh",
"path": "eval.sh"
}
]
@@ -83,9 +83,8 @@
"include": [
"Success: The task was completed correctly."
],
"exclude": [
]
"exclude": []
}
}
}
}
}

7
evaluation_examples/examples/os/4127319a-8b79-4410-b58a-7a151e15f3d7.json
View File

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1mp3bXrhKutWzxHnQc9v2Dtt4xclLemik&export=download&authuser=0&confirm=t&uuid=351dc4ac-ecf6-448b-bb09-ebf1231bfe5a&at=APZUnTUlgWg3o8U2Ghl2xRWEXFjz:1707993730783",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/4127319a-8b79-4410-b58a-7a151e15f3d7/setup.sh",
"path": "setup.sh"
}
]
@@ -52,9 +52,8 @@
"include": [
"54\n"
],
"exclude": [
]
"exclude": []
}
}
}
}
}

7
evaluation_examples/examples/os/4d117223-a354-47fb-8b45-62ab1390a95f.json
View File

@@ -10,7 +10,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=19bEBoYIzwIeTtqSR5Re0XTCN26yXXynn&export=download&authuser=0&confirm=t&uuid=7f9458ab-0e8a-42ff-a10a-eba01f611bc3&at=APZUnTX6GDMmAf-MOSZ58xzrFYS1:1708010153224",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/4d117223-a354-47fb-8b45-62ab1390a95f/setup.sh",
"path": "setup.sh"
}
]
@@ -67,7 +67,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1bLx6ZbtNgNySQrgnX9TrUNjD2zM4mOkA&export=download&authuser=0&confirm=t&uuid=5fa3b3df-e281-484f-b8d4-fcdfad210290&at=APZUnTUrg3BZ2zRykZXH-RQzyGUz:1708010154631",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/4d117223-a354-47fb-8b45-62ab1390a95f/eval.sh",
"path": "eval.sh"
}
]
@@ -93,8 +93,7 @@
"include": [
"All files have the correct permissions."
],
"exclude": [
]
"exclude": []
}
}
}

5
evaluation_examples/examples/os/5812b315-e7bd-4265-b51f-863c02174c28.json
View File

@@ -30,7 +30,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1lOkekinDJRPBqmQN4Xx6pV4WO2uSwKln&export=download&authuser=0&confirm=t&uuid=52b722f4-ec9e-40a1-9b4f-02cb4c5d6b5b&at=APZUnTVY8y0fxhsUBPuc4zC250kv:1707208254033",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/5812b315-e7bd-4265-b51f-863c02174c28/check_password.sh",
"path": "check_password.sh"
}
]
@@ -56,8 +56,7 @@
"include": [
"Password, home directory, and write permission check passed"
],
"exclude": [
]
"exclude": []
}
}
}

9
evaluation_examples/examples/os/5c1075ca-bb34-46a3-a7a0-029bd7463e79.json
View File

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1npIWJR-A78IJ2m0n6aC6Nufa8uUrcpT1&export=download&authuser=0&confirm=t&uuid=668eeed6-3e3f-4f45-997b-19bb578a3f42&at=APZUnTVL1fWbc3PKXWiBVAMPPOJY:1707985593713",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/5c1075ca-bb34-46a3-a7a0-029bd7463e79/setup.sh",
"path": "setup.sh"
}
]
@@ -27,7 +27,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1GeXD_pWlqZ7HCco9RorjzJ_f3DeeP91V&export=download&authuser=0&confirm=t&uuid=9d69de2c-9908-4f6e-ad21-e8329440ee89&at=APZUnTU0uxOOMOi0HuEo2mRLcyjW:1708524614643",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/5c1075ca-bb34-46a3-a7a0-029bd7463e79/eval.sh",
"path": "eval.sh"
}
]
@@ -91,9 +91,8 @@
"include": [
"Evaluation successful."
],
"exclude": [
]
"exclude": []
}
}
}
}
}

7
evaluation_examples/examples/os/5ced85fc-fa1a-4217-95fd-0fb530545ce2.json
View File

@@ -32,7 +32,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=174Bk_JLDwuTTgL0hslzxRG4xB76JxXIR&export=download&authuser=0&confirm=t&uuid=dc3f716f-e21b-4e46-bfa3-6f78b4c11ed4&at=APZUnTVgdfpiWjfBcp32gAuK57Bl:1708526599813",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/5ced85fc-fa1a-4217-95fd-0fb530545ce2/eval.sh",
"path": "eval.sh"
}
]
@@ -58,9 +58,8 @@
"include": [
"Success: The task has been completed correctly."
],
"exclude": [
]
"exclude": []
}
}
}
}
}

22
evaluation_examples/examples/os/5ea617a3-0e86-4ba6-aab2-dac9aa2e8d57.json
View File

@@ -10,7 +10,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1XaTnC_lLbR_tGTz8tcN2Tp6cNrMlNW3R&export=download&authuser=0&confirm=t&uuid=89e69a23-43cf-4316-833a-fb9d3e281460&at=APZUnTWn5zZTH4GlClO6lV1i4WwP:1706184669922",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/5ea617a3-0e86-4ba6-aab2-dac9aa2e8d57/poster_party_night.webp",
"path": "/home/user/Desktop/poster_party_night.webp"
}
]
@@ -39,16 +39,16 @@
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "vm_command_line",
"command": "[ -f /home/user/Desktop/poster_party_night.webp ] && echo 'File exists.' || echo 'File does not exist.'",
"shell": true
},
"expected": {
"type": "rule",
"rules":{
"expected": "File exists.\n"
}
"result": {
"type": "vm_command_line",
"command": "[ -f /home/user/Desktop/poster_party_night.webp ] && echo 'File exists.' || echo 'File does not exist.'",
"shell": true
},
"expected": {
"type": "rule",
"rules": {
"expected": "File exists.\n"
}
}
}
}

7
evaluation_examples/examples/os/6f56bf42-85b8-4fbb-8e06-6c44960184ba.json
View File

@@ -10,7 +10,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1fQGBoTE40BLoNV_d4KYxbYjKRJdIPDio&export=download&authuser=0&confirm=t&uuid=50f5fff6-4c6b-4ce0-b36e-73f0d4bce8ca&at=APZUnTUA_3uAt14q25NN6dCY5X7e:1708531075515",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/6f56bf42-85b8-4fbb-8e06-6c44960184ba/setup.sh",
"path": "setup.sh"
}
]
@@ -57,7 +57,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1BpFAuuH0IHxpWLDF3jaFNxa9QDe_F12D&export=download&authuser=0&confirm=t&uuid=695e8a3c-f354-4e9d-a4c3-e01f149be7be&at=APZUnTVHmmnZVIYLPCbuiQduSZZX:1708531243191",
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/os/6f56bf42-85b8-4fbb-8e06-6c44960184ba/eval.sh",
"path": "eval.sh"
}
]
@@ -83,8 +83,7 @@
"include": [
"Success: file1 exists in dir1.\nSuccess: file1 exists in dir2.\nSuccess: file1 exists in dir3.\n"
],
"exclude": [
]
"exclude": []
}
}
}