将qwen1.8b导出为onnx后，对话时总是会出现イベ，是为什么呢?

xman1991 commented 8 months ago

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

[X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

[X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

将qwen1.8b导出为onnx后，对话时总是会出现イベ

期望行为 | Expected Behavior

将qwen1.8b导出为onnx后，对话时总是不出现イベ

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS:ubuntu20.40
- Python:3.9
- Transformers:4.35.2
- PyTorch:2.0.1
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):11.8

备注 | Anything else?

![Uploading Screenshot from 2024-01-23 14-22-22.png…]()

xman1991 commented 8 months ago

Screenshot from 2024-01-23 14-22-22

bqFirst commented 7 months ago

请问你是如何导出onnx的

shaqing commented 7 months ago

输入是input_ids，然后输出是kv_cache、output_ids，使用torch自带的torch.onnx.export导出

github-actions[bot] commented 5 months ago

This issue has been automatically marked as inactive due to lack of recent activity. Should you believe it remains unresolved and warrants attention, kindly leave a comment on this thread. 此问题由于长期未有新进展而被系统自动标记为不活跃。如果您认为它仍有待解决，请在此帖下方留言以补充信息。

QwenLM / Qwen