from tokenizers import Tokenizer
import onnxruntime as ort
import numpy as np
# 1. Load Tokenizer
tokenizer = Tokenizer.from_pretrained("broadfield-dev/Qwen3-0.6B-20260105-055554-onnx")
# 2. Load Model
session = ort.InferenceSession("model.onnx")
# 3. Inference
text = "Hello world"
encoding = tokenizer.encode(text)
inputs = {
    "input_ids": np.array([encoding.ids], dtype=np.int64),
    "attention_mask": np.array([encoding.attention_mask], dtype=np.int64)
}
logits = session.run(None, inputs)[0]
print(logits.shape)