eye-grep tagger — deberta-v3-small
The accuracy-first tagger for eye-grep, a log colorizer that highlights ids,
timestamps, IPs and repeated strings in server logs. It is a token classifier
that labels each content token of a log line with one of 11 tags, letting a renderer
color site-specific id formats it has never seen before.
Fine-tuned from
microsoft/deberta-v3-small (SentencePiece). This is the champion
model — highest accuracy, larger download — and the eye-grep
CLI loads it by
default. For an in-browser build use the smaller, distilled
opsbr/eye-grep-electra-small.
Tag schema (11 classes)
PUNCT WORD NUM RAND IP DURATION SIZE TIMESTAMP LEVEL URL PATH
RAND is a high-entropy id (uuid / hash / token); NUM, SIZE, DURATION are
numeric values; TIMESTAMP, IP, URL, PATH, LEVEL are self-explanatory;
WORD/PUNCT are ordinary text.
Files
ONNX in the transformers.js layout — onnx/model.onnx (fp32) and
onnx/model_quantized.onnx (int8, the default) — plus the SentencePiece tokenizer.
Usage
eye-grep CLI (this is the default model):
1eye-grep --model opsbr/eye-grep-deberta-v3-small app.log
2# private repo → export HF_TOKEN first
transformers.js:
1import { AutoTokenizer, AutoModelForTokenClassification } from '@huggingface/transformers';
2const tokenizer = await AutoTokenizer.from_pretrained('opsbr/eye-grep-deberta-v3-small');
3const model = await AutoModelForTokenClassification.from_pretrained('opsbr/eye-grep-deberta-v3-small');
Training data
Fine-tuned on the synthetic, fully-owned
opsbr/eye-grep gold set
(Apache-2.0) — deterministically generated, no third-party log data.
Notes
- Int8 dynamic quantization costs only ~0.002 usefulness versus fp32.
- The tokenizer mirrors eye-grep's frozen
train/spec.py; the model's subword
predictions are aligned back onto content-token spans at inference time.
