Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Reranker detected as embedder Jina rerank tiny #500

Open
5 tasks
rawsh-rubrik opened this issue Dec 17, 2024 · 3 comments
Open
5 tasks

Reranker detected as embedder Jina rerank tiny #500

rawsh-rubrik opened this issue Dec 17, 2024 · 3 comments

Comments

@rawsh-rubrik
Copy link

System Info

infinity onnx image latest

Information

  • Docker + cli
  • pip + cli
  • pip + usage of Python interface

Tasks

  • An officially supported CLI command
  • My own modifications

Reproduction

jinaai/jina-reranker-v1-tiny-en
tensorrt device
optimum engine

{"data":[{"id":"jinaai/jina-reranker-v1-tiny-en","stats":{"queue_fraction":0.0,"queue_absolute":0,"results_pending":0,"batch_size":32},"object":"model","owned_by":"infinity","created":1734462700,"backend":"optimum","capabilities":["embed"]}],"object":"list"}
@michaelfeil
Copy link
Owner

https://huggingface.co/jinaai/jina-reranker-v1-tiny-en/discussions/9

Please make the jina team aware of this! @wirthual Already has a PR ready, which currently does not work and needs common resolution.

the model needs to be named “forsequenceclassification” to be detected as sequence classification model.

@rawsh-rubrik
Copy link
Author

@michaelfeil gotcha thanks! will fork for now

@michaelfeil
Copy link
Owner

The name of the model also needs to resolve in the config.json - might need a try or two.

once you got a fork working, use —revision for infinity.

@michaelfeil michaelfeil changed the title Reranker detected as embedder Reranker detected as embedder Jina rerank tiny Dec 17, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants