jfrick's picture
Publish code-focused 32K tokenizer and promote it to the default
0ebdb4f verified
Raw History Blame Contribute Delete
892 Bytes
[
{
"vocab": 16384,
"baseline_size_mib": 64,
"token_change_percent": 13.8842083685768,
"bytes_per_token": 3.2895479620878447
},
{
"vocab": 16384,
"baseline_size_mib": 2048,
"token_change_percent": 14.48309849875795,
"bytes_per_token": 3.2895479620878447
},
{
"vocab": 32768,
"baseline_size_mib": 64,
"token_change_percent": 13.066679257845637,
"bytes_per_token": 3.5474462447867094
},
{
"vocab": 32768,
"baseline_size_mib": 2048,
"token_change_percent": 13.9913345559888,
"bytes_per_token": 3.5474462447867094
},
{
"vocab": 50000,
"baseline_size_mib": 64,
"token_change_percent": 11.982248703193132,
"bytes_per_token": 3.6963237177351083
},
{
"vocab": 50000,
"baseline_size_mib": 2048,
"token_change_percent": 13.048704871757423,
"bytes_per_token": 3.6963237177351083
}
]