A 7-class intent classifier for code query routing. Classifies natural language queries (English and Chinese) into structured intents for code intelligence tools.
Requires
ONNX Runtime. The model takes tokenized text input and outputs sentence embeddings. The classification head (
model_head.json) maps embeddings to intent logits.
Evaluated on a held-out test set of 221 bilingual (Chinese + English) code queries.
Training set: 284 samples. Test set: 221 samples.
int8 (dynamic quantization). Total size ~559MB.
This model is fine-tuned for
C4A (Context For AI), a knowledge modeling service that indexes code repositories and business documents for developer teams and AI agents.