deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B · How to export this model to onnx ?

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Set the model to evaluation mode
model.eval()

# Create dummy input for the model
dummy_input = tokenizer("This is a test input.", return_tensors="pt")

# Define the output path for the ONNX file
onnx_output_path = "deepseek_qwen.onnx"

# Export the model to ONNX
torch.onnx.export(
    model,
    (dummy_input['input_ids'], dummy_input['attention_mask']),  # Input to the model
    onnx_output_path,
    input_names=['input_ids', 'attention_mask'],  # Model input names
    output_names=['logits'],  # Model output names
    dynamic_axes={
        'input_ids': {0: 'batch_size', 1: 'sequence_length'},  # Variable length axes
        'attention_mask': {0: 'batch_size', 1: 'sequence_length'},
        'logits': {0: 'batch_size', 1: 'sequence_length'}
    },
    opset_version=12  # Specify the ONNX opset version
)

print(f"Model exported to {onnx_output_path}")

I am trying export this model with this script. But it failed with following message.

RuntimeError: Only tuples, lists and Variables are supported as JIT inputs/outputs. Dictionaries and strings are also accepted, but their usage is not recommended. Here, received an input of unsupported type: DynamicCache

how to fix?