jfrick's picture
Publish code-focused 32K tokenizer and promote it to the default
0ebdb4f verified
Raw History Blame Contribute Delete
5.05 kB
[
{
"vocab": 16384,
"category": "python",
"baseline_size_mib": 64,
"token_saving_percent": 5.161717709235713,
"paired_ci95": [
4.805887801278443,
5.518307765192585
]
},
{
"vocab": 16384,
"category": "python",
"baseline_size_mib": 2048,
"token_saving_percent": 4.554172839072024,
"paired_ci95": [
4.2022398257968305,
4.8870282779627345
]
},
{
"vocab": 16384,
"category": "json",
"baseline_size_mib": 64,
"token_saving_percent": 11.49778915522458,
"paired_ci95": [
11.051183144800918,
11.937857395041755
]
},
{
"vocab": 16384,
"category": "json",
"baseline_size_mib": 2048,
"token_saving_percent": 10.045900258891184,
"paired_ci95": [
9.62401271480091,
10.448147880543663
]
},
{
"vocab": 16384,
"category": "git_diff",
"baseline_size_mib": 64,
"token_saving_percent": 14.381806036692401,
"paired_ci95": [
13.52058267964924,
15.107384868191106
]
},
{
"vocab": 16384,
"category": "git_diff",
"baseline_size_mib": 2048,
"token_saving_percent": 14.181835168086199,
"paired_ci95": [
13.483675527600566,
14.828775308338756
]
},
{
"vocab": 16384,
"category": "tool_call",
"baseline_size_mib": 64,
"token_saving_percent": 17.040354513346145,
"paired_ci95": [
16.288536671705394,
17.857604436611496
]
},
{
"vocab": 16384,
"category": "tool_call",
"baseline_size_mib": 2048,
"token_saving_percent": 16.768112786628674,
"paired_ci95": [
16.00072559221649,
17.65307903734406
]
},
{
"vocab": 32768,
"category": "python",
"baseline_size_mib": 64,
"token_saving_percent": 3.715102495292788,
"paired_ci95": [
3.416089462295272,
3.98995603061774
]
},
{
"vocab": 32768,
"category": "python",
"baseline_size_mib": 2048,
"token_saving_percent": 2.8060044548773977,
"paired_ci95": [
2.5062225893620456,
3.0750785140490904
]
},
{
"vocab": 32768,
"category": "json",
"baseline_size_mib": 64,
"token_saving_percent": 8.836071797497858,
"paired_ci95": [
8.489760736047739,
9.168205525309618
]
},
{
"vocab": 32768,
"category": "json",
"baseline_size_mib": 2048,
"token_saving_percent": 8.21369838659496,
"paired_ci95": [
7.84936586072181,
8.534293914918637
]
},
{
"vocab": 32768,
"category": "git_diff",
"baseline_size_mib": 64,
"token_saving_percent": 12.523581002813177,
"paired_ci95": [
11.74804909818136,
13.237170838119336
]
},
{
"vocab": 32768,
"category": "git_diff",
"baseline_size_mib": 2048,
"token_saving_percent": 11.833480661140483,
"paired_ci95": [
11.044209250897488,
12.573471647810612
]
},
{
"vocab": 32768,
"category": "tool_call",
"baseline_size_mib": 64,
"token_saving_percent": 14.702971974651803,
"paired_ci95": [
13.87174606871349,
15.585460177596222
]
},
{
"vocab": 32768,
"category": "tool_call",
"baseline_size_mib": 2048,
"token_saving_percent": 13.967104858390922,
"paired_ci95": [
13.094244188134251,
14.86115232472458
]
},
{
"vocab": 50000,
"category": "python",
"baseline_size_mib": 64,
"token_saving_percent": 2.76451113616184,
"paired_ci95": [
2.507650374711118,
3.0204865576016524
]
},
{
"vocab": 50000,
"category": "python",
"baseline_size_mib": 2048,
"token_saving_percent": 1.6333682923995951,
"paired_ci95": [
1.3690041312459533,
1.8792020981977022
]
},
{
"vocab": 50000,
"category": "json",
"baseline_size_mib": 64,
"token_saving_percent": 7.215038631382765,
"paired_ci95": [
6.885572584118245,
7.538642446610321
]
},
{
"vocab": 50000,
"category": "json",
"baseline_size_mib": 2048,
"token_saving_percent": 7.160854468004696,
"paired_ci95": [
6.8230077267262095,
7.490274125295937
]
},
{
"vocab": 50000,
"category": "git_diff",
"baseline_size_mib": 64,
"token_saving_percent": 7.743693886276182,
"paired_ci95": [
7.125926910643197,
8.312421798378304
]
},
{
"vocab": 50000,
"category": "git_diff",
"baseline_size_mib": 2048,
"token_saving_percent": 7.129920200842821,
"paired_ci95": [
6.607120345561133,
7.644764143960624
]
},
{
"vocab": 50000,
"category": "tool_call",
"baseline_size_mib": 64,
"token_saving_percent": 13.145045375119778,
"paired_ci95": [
12.422289981936078,
13.92135869878892
]
},
{
"vocab": 50000,
"category": "tool_call",
"baseline_size_mib": 2048,
"token_saving_percent": 12.696928813487297,
"paired_ci95": [
11.968021889121987,
13.519645028868915
]
}
]