infinity icon indicating copy to clipboard operation
infinity copied to clipboard

Reranker detected as embedder Jina rerank tiny

Open rawsh-rubrik opened this issue 11 months ago • 3 comments
trafficstars

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"}

rawsh-rubrik avatar Dec 17 '24 19:12 rawsh-rubrik

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.

michaelfeil avatar Dec 17 '24 19:12 michaelfeil

@michaelfeil gotcha thanks! will fork for now

rawsh-rubrik avatar Dec 17 '24 19:12 rawsh-rubrik

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 avatar Dec 17 '24 20:12 michaelfeil