code-sprout-30m / data_report.json
Raymond1938-4's picture
Release experimental CodeSprout 30M checkpoint
61790a1 verified
Raw History Blame Contribute Delete
956 Bytes
{
"files": 812,
"train_files": 732,
"validation_files": 80,
"languages": {
"html": {
"files": 151,
"characters": 273690
},
"javascript": {
"files": 186,
"characters": 718480
},
"python": {
"files": 71,
"characters": 588229
},
"typescript": {
"files": 404,
"characters": 7659467
}
},
"sources": [
[
"expressjs/express",
"9efc29e280018dafc1f0617f3a3d28f4e463b7be",
"MIT"
],
[
"mdn/learning-area",
"d55e1c2e3ff401519811b64e5b2a7d3643b43d0f",
"CC0-1.0"
],
[
"microsoft/TypeScript",
"c63de15a992d37f0d6cec03ac7631872838602cb",
"Apache-2.0"
],
[
"pallets/flask",
"d086db856be187255b8ec61ef409357393020f32",
"BSD-3-Clause"
]
],
"deduplication": "SHA256 exact file dedup; file-disjoint split, not repository-disjoint"
}