Qwen

/

CodeQwen1.5-7B-Chat

like 205

Hi community,

I tried exporting the Qwen to ONNX model using the command -

optimum-cli export onnx --model Qwen/CodeQwen1.5-7B-Chat --framework pt --task text-generation-with-past Qwen/CodeQwen1.5-7B-Chat

and successfully retrieved a .onnx model.
Now while trying to convert it to FP16/INT4 precision, I am facing the error stating it has exceeded protobuff memory capacity of 2GB as -

What should be the next step for this conversion ?