Exported to ONNX (opset 17) via optimum and served as an ONNX Runtime backend model inside NVIDIA Triton Inference Server on GKE Autopilot (NVIDIA L4 GPU).

Usage

Base model: distilbert/distilbert-base-uncased
Dataset: 91 hand-curated examples (SQL=30, FINANCIAL=30, GENERAL=31)
Epochs: 5
Learning rate: 2e-5
Batch size: 16
Max sequence length: 128
Optimizer: AdamW (weight_decay=0.01)
Val split: 20% stratified

python

from transformers import pipeline

classifier = pipeline("text-classification", model="xczou/distilbert-intent-sql-financial-general")
classifier("Write a SQL query to find all orders above 100")
# [{'label': 'SQL', 'score': 0.98}]