mirror of
https://github.com/hanzoai/benchmarks.git
synced 2026-10-30 14:59:11 +00:00
zeekayandHanzo Dev
c44f70eed2
Copied from hanzoai/decision results/laya/parity.json: max logit difference 2.9e-5 and max probability difference 6.2e-6 against a 1e-4 bound, across nine behaviours and a twelve-language set, on all three checkpoints. Co-authored-by: Hanzo Dev <[email protected]>
46 lines
1.1 KiB
JSON
46 lines
1.1 KiB
JSON
{
|
|
"states": 21,
|
|
"languages": [
|
|
"ar",
|
|
"zh",
|
|
"ja",
|
|
"ko",
|
|
"hi",
|
|
"he",
|
|
"th",
|
|
"km",
|
|
"fr",
|
|
"es",
|
|
"de",
|
|
"en"
|
|
],
|
|
"checkpoints": [
|
|
{
|
|
"id": "laya",
|
|
"repo": "hanzoai/kai-1",
|
|
"revision": "b50502c28537df49a3621f6fa543f9e8521e8a9c",
|
|
"sha256": "891102d372688fc2a094dac56a384bc537b87c63f21f9f3dac0be2b7cbc8d86c",
|
|
"calibration": "cal_ad93eae1cf0e34a6"
|
|
},
|
|
{
|
|
"id": "laya-multilingual",
|
|
"repo": "hanzoai/kai-1-multilingual",
|
|
"revision": "3119843b5261e34903f93d03813467524c57982e",
|
|
"sha256": "9d628fd971b700382ac6f65920a86f149777b2e748e0c955fb3b19695aa8f204",
|
|
"calibration": "cal_6ceaa0b335b599b1"
|
|
},
|
|
{
|
|
"id": "laya-agent",
|
|
"repo": "hanzoai/kai-1-agent",
|
|
"revision": "e3e416499b8a983d2aa0bcc684d5457ad6bfd6a1",
|
|
"sha256": "4fa56de72383a9d3efa9cfa78955733c81b9fc8067a587ca4beb82c78107a24e",
|
|
"calibration": "cal_6dbb072f8109a222"
|
|
}
|
|
],
|
|
"labels": 108,
|
|
"labels_equal": 108,
|
|
"max_logit": 0.0000286102294921875,
|
|
"max_prob": 6.198883056640625e-6,
|
|
"bound": 0.0001
|
|
}
|