jfrick's picture
Publish code-focused 32K tokenizer and promote it to the default
0ebdb4f verified
Raw History Blame Contribute Delete
1.76 kB
{
"name": "focused-64mib-32768",
"vocab": 32768,
"execution": "modal-cpu",
"tokenizer_sha256": "add5b2c7542e4efded329735825ecdcb94df1432617c3d3e4b7508aa459432f9",
"evaluation_sha256": "a9a82723c1e78b46ec52b33b81551a61a5498e46ac73a6f09e4c0da9e27775a0",
"metrics": {
"python": {
"bytes": 2513044,
"tokens": 615688,
"examples": 512,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 4.08168422967477,
"mean_tokens_per_example": 1202.515625,
"p95_tokens_per_example": 2184
},
"json": {
"bytes": 2782302,
"tokens": 722785,
"examples": 512,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.849418568453966,
"mean_tokens_per_example": 1411.689453125,
"p95_tokens_per_example": 2514
},
"git_diff": {
"bytes": 187152,
"tokens": 52862,
"examples": 512,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.5403881805455715,
"mean_tokens_per_example": 103.24609375,
"p95_tokens_per_example": 249
},
"tool_call": {
"bytes": 965682,
"tokens": 251703,
"examples": 512,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.8365931276146887,
"mean_tokens_per_example": 491.607421875,
"p95_tokens_per_example": 2304
}
},
"fragmentation": {
"{\"name\":\"read_file\",\"arguments\":{\"path\":\"src/main.py\"}}": 14,
"diff --git a/main.py b/main.py\n@@ -1,2 +1,2 @@\n-old\n+new\n": 25,
"get_user_configuration": 3,
"\"additionalProperties\":false": 4,
"\"tool_call_id\":\"call_0123456789\"": 12
},
"correctness_passed": true,
"family": "focused",
"size_mib": 64
}