from pathlib import Path

from sentence_transformers import SentenceTransformer

model_dir = Path("miniLM-onnx-int8")
model = SentenceTransformer(
    str(model_dir),
    backend="onnx",
    model_kwargs={"file_name": "onnx/model_quint8_avx2.onnx"},
)

embeddings = model.encode(["Dynamic ONNX quantization reduces CPU model size."])
print(f"backend: {model.backend}")
print(f"embedding shape: {embeddings.shape}")
print(f"embedding dtype: {embeddings.dtype}")