Problem converting tinyllama to onnx model with optimum-cli

[hayyaw]

System Info

main branch newest
local pip install

Who can help?

@michaelbenayoun

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction (minimal, reproducible, runnable)

optimum-cli export onnx --model /home/wangzhiqun/TinyLlama-1.1B-Chat-v1.0 --task text-generation --batch_size 1 --sequence_length 128 tinyllama_onnx_file

Expected behavior

To specify the batch_size and sequence_length, I use the following "optimum-cli export onnx --model /home/wangzhiqun/TinyLlama-1.1B-Chat-v1.0 --task text-generation --batch_size 1 --sequence_length 128 tinyllama_onnx_file". But the exported onnx model still holds the shape [batch_size, sequence_length]. How can I specify the fixed dimensions?