from pathlib import Path

from sentence_transformers import SentenceTransformer, export_dynamic_quantized_onnx_model

model_id = "sentence-transformers/all-MiniLM-L6-v2"
output_dir = Path("miniLM-onnx-int8")
output_dir.mkdir(parents=True, exist_ok=True)

model = SentenceTransformer(
    model_id,
    backend="onnx",
    model_kwargs={"file_name": "onnx/model.onnx"},
)
model.save_pretrained(str(output_dir))

export_dynamic_quantized_onnx_model(
    model,
    "avx2",
    str(output_dir),
)

quantized_file = output_dir / "onnx" / "model_quint8_avx2.onnx"
print(f"saved: {quantized_file}")
print(f"exists: {quantized_file.exists()}")
print(f"bytes: {quantized_file.stat().st_size}")