[Bug]: towhee build docker image error with a local private BERT model

[drow931]

Is there an existing issue for this?

• [X] I have searched the existing issues

Current Behavior

When executing towhee.build_docker_image, the op contains a local private BERT model, and the following error occurs: factory.py-factory:118 - ERROR: Loading operator with error: yyyy/chinese-bert-wwm-ext is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'

Which level directory in the docker should this model be copied to?

Expected Behavior

No response

Steps To Reproduce

No response

Environment

- Towhee version(e.g. v0.1.3 or 8b23a93):
- OS(Ubuntu or CentOS): centos7
- CPU/Memory:
- GPU: T4
- Others: cuda 11.7

Anything else?

No response

[junjiejiangjjj]

Use towhee.build_pipeline_model to create Triton models without using Docker. wiki: https://towhee.readthedocs.io/en/latest/triton/triton.html

And then build a docker image to run the models, need to install some deps Some example dockerfiles: https://github.com/towhee-io/towhee/tree/main/towhee/serve/triton/dockerfiles

[drow931]

nice

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. Rotten issues close after 30d of inactivity. Close the stale issues and pull requests after 7 days of inactivity. Reopen the issue with /reopen.